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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Women
    -0.07
    equalTo
    -0.07
    .Immutable
    -0.06
     yoga
    -0.06
     Editor
    -0.06
     ANN
    -0.06
     wolf
    -0.06
    perse
    -0.06
    Arr
    -0.06
    Override
    -0.06
    POSITIVE LOGITS
    怪
    0.06
    ifax
    0.06
     bé
    0.06
    (DWORD
    0.06
    ‚
    0.06
    œ
    0.06
    拳
    0.06
    .onreadystatechange
    0.06
     čer
    0.06
    ไ
    0.06
    Act Density 0.021%

    No Known Activations