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

    Neuronpedia

    INDEX
    Explanations

    Chinese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    昀
    -0.07
    emailer
    -0.07
     знач
    -0.06
    .fetch
    -0.06
    ichen
    -0.06
     tart
    -0.06
     blessed
    -0.06
     stationed
    -0.06
    Serializer
    -0.06
    (h
    -0.06
    POSITIVE LOGITS
    與
    0.08
    与
    0.08
    随
    0.07
    وات
    0.07
    یر
    0.07
    _crit
    0.07
    malink
    0.07
    ניו
    0.06
    cial
    0.06
     autob
    0.06
    Act Density 0.020%

    No Known Activations