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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，加
    -0.07
     quan
    -0.06
    ycin
    -0.06
     ---
    -0.06
    alamat
    -0.06
     shortage
    -0.06
    籍
    -0.06
     bureau
    -0.06
    淡
    -0.06
     pos
    -0.06
    POSITIVE LOGITS
     penal
    0.08
    finding
    0.06
    ultiply
    0.06
    」↵↵
    0.06
    Guid
    0.06
    currentColor
    0.06
    Dirty
    0.06
     ducks
    0.06
     neutr
    0.06
     路
    0.06
    Act Density 0.106%

    No Known Activations