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

    Neuronpedia

    INDEX
    Explanations

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     narrator
    -0.09
    ంగా
    -0.09
     الحلقة
    -0.08
    ాం�
    -0.08
    Display
    -0.08
     జరిగింది
    -0.08
     rur
    -0.08
     utils
    -0.08
    ార్
    -0.08
     display
    -0.07
    POSITIVE LOGITS
     veto
    0.10
     Zustimmung
    0.10
     નિર્ણ
    0.09
     ক্ষম
    0.09
     Entscheidungen
    0.09
     decisiones
    0.09
     영향
    0.09
    决
    0.09
     승인
    0.09
     সিদ্ধান্ত
    0.08
    Act Density 0.023%

    No Known Activations