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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pow
    -0.06
     Tanrı
    -0.06
     lender
    -0.06
     scary
    -0.06
     Ability
    -0.06
    َت
    -0.06
    _Em
    -0.06
    complexContent
    -0.06
     celý
    -0.06
    дут
    -0.06
    POSITIVE LOGITS
     manifesto
    0.07
     subparagraph
    0.07
    /licenses
    0.06
    `(
    0.06
    �
    0.06
     fabs
    0.06
    /\
    0.06
    �장
    0.06
    ivated
    0.06
    ขณะท
    0.06
    Act Density 0.000%

    No Known Activations