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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical objects and structures

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

    parts of structures or objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ratio
    -0.40
    Sincerely
    -0.39
     direction
    -0.37
    __*/
    -0.35
     cobr
    -0.34
     escalation
    -0.34
     inspiration
    -0.34
    Heraus
    -0.33
     escal
    -0.33
    google
    -0.32
    POSITIVE LOGITS
     ligiloj
    0.66
    parsedMessage
    0.66
    makeText
    0.62
    tanleria
    0.62
    ніципалі
    0.60
    afficheront
    0.60
    awtextra
    0.56
     digitais
    0.53
     plufieurs
    0.52
    CloseOperation
    0.51
    Act Density 0.059%

    No Known Activations