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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _setopt
    -0.07
    으로
    -0.07
    391
    -0.06
     многие
    -0.06
     раск
    -0.06
     statute
    -0.06
    36
    -0.06
    evenodd
    -0.06
    361
    -0.06
     glorious
    -0.06
    POSITIVE LOGITS
    <U
    0.08
     AR
    0.07
     MIT
    0.07
    _Reference
    0.07
     Salv
    0.07
    ارهای
    0.07
    -write
    0.06
     MV
    0.06
    اليا
    0.06
    legation
    0.06
    Act Density 0.108%

    No Known Activations