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

    Neuronpedia

    INDEX
    Explanations

    descriptive evaluations of experiences or performances

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

    Positive subjective evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COVID
    -0.35
     sup
    -0.32
    ⎪
    -0.31
     EP
    -0.30
    rebbe
    -0.28
    IContainer
    -0.28
    EP
    -0.27
     EEUU
    -0.27
    ready
    -0.27
    sträger
    -0.27
    POSITIVE LOGITS
    GTCX
    0.71
    extAlignment
    0.66
     NSCoder
    0.65
    AndEndTag
    0.64
    ValueStyle
    0.63
    TagMode
    0.63
    StructEnd
    0.62
     ErrIntOverflow
    0.60
    tvguidetime
    0.60
    ThroughAttribute
    0.58
    Act Density 0.097%

    No Known Activations