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

    Neuronpedia

    INDEX
    Explanations

    Health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _KEYS
    -0.07
     StatusCode
    -0.06
    icio
    -0.06
    ']:↵
    -0.06
     sqrt
    -0.06
     Medical
    -0.06
    NORMAL
    -0.06
    385
    -0.06
     mc
    -0.06
     zdroj
    -0.06
    POSITIVE LOGITS
     Eventually
    0.06
     doivent
    0.06
    phans
    0.06
    OfDay
    0.06
    IGNAL
    0.06
    (b
    0.06
     KNOW
    0.06
    année
    0.06
     jej
    0.06
    (tok
    0.06
    Act Density 0.010%

    No Known Activations