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

    Neuronpedia

    INDEX
    Explanations

    witness testimony

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nos
    -0.07
     Esk
    -0.06
    _lc
    -0.06
     Gould
    -0.06
    iscrimination
    -0.06
    .model
    -0.06
     magnitude
    -0.06
    ören
    -0.06
     ServiceProvider
    -0.06
     individuals
    -0.06
    POSITIVE LOGITS
    YGON
    0.07
    (@(
    0.07
     patched
    0.07
    (platform
    0.06
    黎
    0.06
    .Priority
    0.06
     дів
    0.06
     fotoğraf
    0.06
    _TOO
    0.06
     antis
    0.06
    Act Density 0.032%

    No Known Activations