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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     территории
    -0.07
    _macros
    -0.07
    .ro
    -0.06
    .undefined
    -0.06
    nesty
    -0.06
     hashes
    -0.06
    $IFn
    -0.06
    -либо
    -0.06
     impunity
    -0.06
    75
    -0.06
    POSITIVE LOGITS
    （笑
    0.07
    (tv
    0.06
     gift
    0.06
    nze
    0.06
    (vo
    0.06
    654
    0.06
    BadRequest
    0.06
    crit
    0.06
     Telephone
    0.06
    trag
    0.06
    Act Density 0.003%

    No Known Activations