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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical or scientific notation indicators

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

    code and math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.79
    unknownFields
    -0.71
    ImageContext
    -0.70
    awtextra
    -0.68
    WebVitals
    -0.67
    principalColumn
    -0.66
    省市镇
    -0.66
    ⟬
    -0.63
     PeEnEo
    -0.62
     surla
    -0.62
    POSITIVE LOGITS
    //
    0.46
     //
    0.33
    тя
    0.33
    спект
    0.33
     aspect
    0.33
    cert
    0.32
    util
    0.31
    向
    0.31
    /*
    0.31
     Verenigde
    0.31
    Act Density 0.002%

    No Known Activations