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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Form
    -0.07
    WRITE
    -0.07
    463
    -0.07
     atof
    -0.07
    床
    -0.06
     ohne
    -0.06
    lopen
    -0.06
    대표
    -0.06
     legs
    -0.06
     polož
    -0.06
    POSITIVE LOGITS
    AFP
    0.06
    UNE
    0.06
    [H
    0.06
    ?,
    0.06
     krás
    0.06
    러스
    0.06
     piş
    0.06
    TriState
    0.06
    ACION
    0.06
    ẹp
    0.06
    Act Density 0.003%

    No Known Activations