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

    Neuronpedia

    INDEX
    Explanations

    laboratory settings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    百
    -0.07
     Equity
    -0.06
    ZONE
    -0.06
    -business
    -0.06
    u
    -0.06
     Significant
    -0.06
    erging
    -0.06
    559
    -0.06
    399
    -0.06
     decides
    -0.06
    POSITIVE LOGITS
    .Phone
    0.07
    _kelas
    0.07
     Garten
    0.07
     images
    0.06
     ReSharper
    0.06
    часно
    0.06
    ppy
    0.06
     Tân
    0.06
    (fn
    0.06
    PERATURE
    0.06
    Act Density 0.094%

    No Known Activations