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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their comparisons or operations

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

    7 followed by numbers or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.51
     myſelf
    -0.46
     tantum
    -0.45
     lomb
    -0.40
    NodeType
    -0.40
    Zone
    -0.40
     anſ
    -0.40
     autop
    -0.39
     onView
    -0.39
    Optional
    -0.39
    POSITIVE LOGITS
     OMITBAD
    0.76
    Personendaten
    0.68
    ⟬
    0.61
    évaluateur
    0.59
    Personensuche
    0.58
     Autorisations
    0.56
    enumii
    0.54
    ContentLoaded
    0.53
     Normdatei
    0.53
    Geplaatst
    0.52
    Act Density 0.051%

    No Known Activations