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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вы
    -0.08
     выб
    -0.08
     responded
    -0.08
    راعة
    -0.07
     Records
    -0.07
     Questions
    -0.07
     olmaq
    -0.07
     reacted
    -0.07
     William
    -0.07
     argued
    -0.07
    POSITIVE LOGITS
    -version
    0.09
     mất
    0.08
     versions
    0.08
    版本
    0.08
     inconsist
    0.08
     discrepancies
    0.08
    aff
    0.08
     jamais
    0.07
     denomin
    0.07
    ामुळे
    0.07
    Act Density 0.018%

    No Known Activations