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

    Neuronpedia

    INDEX
    Explanations

    modifiers indicating certainty or uncertainty in actions or states

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

    acting simply or automatically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ніципалі
    -0.53
    webElementXpaths
    -0.50
    $_['
    -0.49
     Италијани
    -0.46
     typelib
    -0.40
     Obrador
    -0.40
     SwitchCompat
    -0.40
    stylers
    -0.39
    ViewFeatures
    -0.39
    IsMutable
    -0.38
    POSITIVE LOGITS
     willy
    0.46
     blindly
    0.44
     neglect
    0.43
    adop
    0.42
    nesc
    0.42
     Huck
    0.42
    참고
    0.41
    frastructure
    0.41
     passively
    0.41
    abandon
    0.40
    Act Density 0.024%

    No Known Activations