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

    Neuronpedia

    INDEX
    Explanations

    phrases describing rarity or challenges in common situations

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

    not uncommon / not hard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.46
     Lingkungan
    -0.44
     extranjera
    -0.44
     pouvoit
    -0.44
     provisoire
    -0.43
     démocratique
    -0.43
     judiciaire
    -0.42
     thermique
    -0.41
     appartiennent
    -0.40
     rempliss
    -0.40
    POSITIVE LOGITS
    Filmografie
    0.60
     uncommon
    0.59
    .$.
    0.57
    ::_('
    0.56
     handleMessage
    0.53
    BASEPATH
    0.52
    comparable
    0.52
    Personensuche
    0.52
    setObjectName
    0.50
     CURIAM
    0.50
    Act Density 0.009%

    No Known Activations