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

    Neuronpedia

    INDEX
    Explanations

    references to female and male pronouns

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

    pronouns referring to people/entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taktlose
    -0.49
    ragalactic
    -0.44
    енча
    -0.42
     jenner
    -0.42
    TAWA
    -0.42
    Numerology
    -0.42
    FTA
    -0.42
    AutoScaleMode
    -0.40
     fVar
    -0.39
    SizeMode
    -0.39
    POSITIVE LOGITS
    writeValue
    0.44
     zijne
    0.42
     blij
    0.42
     sitten
    0.41
    &__
    0.40
    ningss
    0.40
    stateProvider
    0.40
     näytte
    0.40
     behulp
    0.39
    Erreferentziak
    0.39
    Act Density 0.146%

    No Known Activations