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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /renderer
    -0.07
    jualan
    -0.07
     anxious
    -0.06
     sar
    -0.06
     及
    -0.06
    riminal
    -0.06
    .readline
    -0.06
    American
    -0.06
    -IN
    -0.06
     synchronize
    -0.06
    POSITIVE LOGITS
     THESE
    0.06
    _DE
    0.06
    mist
    0.06
     aj
    0.06
     prepend
    0.06
    -driving
    0.06
    UNKNOWN
    0.06
    _baseline
    0.06
     dumping
    0.06
     ihtiy
    0.06
    Act Density 0.021%

    No Known Activations