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

    Neuronpedia

    INDEX
    Explanations

    scientific context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    312
    -0.07
     حي
    -0.07
    ६
    -0.06
    920
    -0.06
     bas
    -0.06
    _seq
    -0.06
     fortn
    -0.06
     Developers
    -0.06
    991
    -0.06
    (num
    -0.06
    POSITIVE LOGITS
     without
    0.06
     ukon
    0.06
     Feld
    0.06
    _est
    0.06
    icap
    0.06
    Denver
    0.06
    _MISS
    0.06
    kelig
    0.06
    ienen
    0.06
     stellen
    0.06
    Act Density 0.034%

    No Known Activations