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

    Neuronpedia

    INDEX
    Explanations

    Simplicity and ease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，這
    -0.07
     بأن
    -0.06
     دخ
    -0.06
    Diese
    -0.06
    、三
    -0.06
     whose
    -0.06
     rotated
    -0.06
     those
    -0.06
     přist
    -0.06
     أو
    -0.06
    POSITIVE LOGITS
     gaz
    0.07
    _written
    0.07
     TP
    0.07
    Required
    0.07
    _template
    0.07
    lead
    0.06
     tc
    0.06
     composite
    0.06
     мин
    0.06
    PLE
    0.06
    Act Density 0.115%

    No Known Activations