Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to publishing and authority figures involving decision-making and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "the ref" describing referee actions

    np_acts-logits-general · gemini-2.0-flash

    officials and referees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.61
    ViewFeatures
    -0.58
    SourceChecksum
    -0.53
    onViewCreated
    -0.52
     MainAxisSize
    -0.51
    buttonBar
    -0.42
    LookAnd
    -0.42
     betweenstory
    -0.42
     numberOfRows
    -0.42
    QMetaType
    -0.41
    POSITIVE LOGITS
     Administrativna
    0.42
    ThroughAttribute
    0.42
     المعيارى
    0.41
     Officials
    0.41
     OFFIC
    0.40
    phazard
    0.40
    Officials
    0.36
     ब्रेकडाउन
    0.35
     imposed
    0.35
     permiti
    0.35
    Act Density 0.551%

    No Known Activations