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

    Neuronpedia

    INDEX
    Explanations

    A.J. names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     способом
    -0.06
    Currency
    -0.06
     Пра
    -0.06
    <Boolean
    -0.06
    (review
    -0.06
    (z
    -0.06
    'hui
    -0.06
    ingen
    -0.06
    -fiction
    -0.06
     cq
    -0.06
    POSITIVE LOGITS
     Aj
    0.07
    ju
    0.07
    /es
    0.07
     objev
    0.07
     Buff
    0.07
    osloven
    0.06
     ED
    0.06
     bid
    0.06
     JJ
    0.06
     uploads
    0.06
    Act Density 0.003%

    No Known Activations