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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рек
    -0.07
    “If
    -0.07
    Terminal
    -0.07
    дает
    -0.06
     sao
    -0.06
     jackpot
    -0.06
    γγραφ
    -0.06
     нею
    -0.06
    Payment
    -0.06
    .Private
    -0.06
    POSITIVE LOGITS
     Viagra
    0.06
    (Byte
    0.06
     era
    0.06
     μέχρι
    0.06
    zin
    0.06
     NIH
    0.06
     repar
    0.06
    apid
    0.06
    ‌المللی
    0.06
    ness
    0.06
    Act Density 0.031%

    No Known Activations