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

    Neuronpedia

    INDEX
    Explanations

    many, several

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kinds
    -0.07
    stri
    -0.07
     chir
    -0.07
     surprise
    -0.06
    chrom
    -0.06
     orden
    -0.06
     تش
    -0.06
    -ind
    -0.06
    、日本
    -0.06
     chunk
    -0.06
    POSITIVE LOGITS
    _argv
    0.07
    isNull
    0.07
    قى
    0.07
     setValue
    0.06
     Powell
    0.06
    ouncill
    0.06
     OPTION
    0.06
     Barrett
    0.06
    subtype
    0.06
     लगभग
    0.06
    Act Density 0.013%

    No Known Activations