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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
            ↵↵
    -0.07
     tamb
    -0.07
    .Printf
    -0.07
    .default
    -0.07
    best
    -0.07
     ::=
    -0.07
    //--
    -0.06
     مربع
    -0.06
     نيز
    -0.06
     evoke
    -0.06
    POSITIVE LOGITS
     apology
    0.06
     Joh
    0.06
     written
    0.06
     newText
    0.06
     Physician
    0.06
    ר
    0.06
    ологичес
    0.06
    IFT
    0.06
     března
    0.06
    izado
    0.06
    Act Density 0.024%

    No Known Activations