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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Managing
    -0.07
     coincidence
    -0.07
    tyard
    -0.07
    _cluster
    -0.07
     tooltips
    -0.06
     Automated
    -0.06
     reflective
    -0.06
    .exec
    -0.06
     culpa
    -0.06
     Trou
    -0.06
    POSITIVE LOGITS
    isNew
    0.07
    dates
    0.06
    [T
    0.06
     Suppress
    0.06
    spy
    0.06
     poc
    0.06
    ピー
    0.06
     unm
    0.06
    _more
    0.06
     thấp
    0.06
    Act Density 0.029%

    No Known Activations