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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that indicate a connection between ideas or phrases

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

    disrespectful, shocking, exhausting, inflexible, sad, dumb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     camiset
    -0.50
     meia
    -0.49
    transQ
    -0.49
    🔕
    -0.46
     Unterneh
    -0.46
    โท
    -0.45
    Gön
    -0.45
    Grüsse
    -0.44
     montanha
    -0.44
     sidang
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.63
    MigrationBuilder
    0.60
     StatelessWidget
    0.55
    IntoConstraints
    0.50
    WriteTagHelper
    0.50
    ValueStyle
    0.47
     onBind
    0.46
    IsMutable
    0.44
    存于互联网档案馆
    0.41
     فريبيس
    0.40
    Act Density 0.018%

    No Known Activations