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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aff
    -0.06
     rele
    -0.06
    Leg
    -0.06
    oğan
    -0.06
     bisc
    -0.06
     Gram
    -0.06
     resign
    -0.06
    Season
    -0.06
     Spare
    -0.06
     حرف
    -0.06
    POSITIVE LOGITS
     Montana
    0.07
    (td
    0.07
     -->↵↵
    0.07
     ↵ ↵
    0.07
     خیلی
    0.07
    ensively
    0.07
     error
    0.07
     Texas
    0.07
     lign
    0.06
    —and
    0.06
    Act Density 0.000%

    No Known Activations