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

    Neuronpedia

    INDEX
    Explanations

    code and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Factors
    -0.07
     div
    -0.07
    estone
    -0.06
    .sessions
    -0.06
    ()['
    -0.06
    lexer
    -0.06
    Destroy
    -0.06
     ['./
    -0.06
    prevState
    -0.06
    /stretch
    -0.06
    POSITIVE LOGITS
     طبي
    0.07
     fragrance
    0.07
     conform
    0.06
     DVD
    0.06
     کار
    0.06
     ，
    0.06
     더욱
    0.06
     not
    0.06
    .FONT
    0.06
    /il
    0.06
    Act Density 0.056%

    No Known Activations