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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and interactions involving the speaker

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

    object pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     primary
    -0.38
    hofen
    -0.35
     []).
    -0.35
     createState
    -0.32
     gain
    -0.32
     continúas
    -0.32
     saker
    -0.31
     Primary
    -0.31
     pic
    -0.31
     secondary
    -0.30
    POSITIVE LOGITS
    +#+
    0.71
    AISSEE
    0.65
    ThroughAttribute
    0.63
     kasarigan
    0.63
    şört
    0.62
    0.59
    WriteBarrier
    0.59
    writeFieldEnd
    0.57
    IsMutable
    0.55
    InjectAttribute
    0.54
    Act Density 0.089%

    No Known Activations