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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     המי
    -0.07
     rendez
    -0.07
     thinly
    -0.07
    任何人都
    -0.07
    деся
    -0.07
    [C
    -0.07
    _cred
    -0.07
    殓
    -0.07
    借
    -0.06
    ['_
    -0.06
    POSITIVE LOGITS
    Hit
    0.07
     getList
    0.07
    -fix
    0.07
    linux
    0.07
    _horizontal
    0.07
    -mean
    0.07
    /span
    0.07
    .line
    0.07
    button
    0.07
    😆
    0.07
    Act Density 0.023%

    No Known Activations