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

    Neuronpedia

    INDEX
    Explanations

    provide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outwe
    -0.09
     sparked
    -0.09
     ஒன்று
    -0.08
     sheds
    -0.08
     നിരവധി
    -0.08
     Netflix
    -0.08
     naanị
    -0.08
     sabotage
    -0.08
     અનેક
    -0.08
     الوحيد
    -0.08
    POSITIVE LOGITS
     Regarding
    0.10
    分别
    0.10
     remarks
    0.10
     Additional
    0.10
    Regarding
    0.10
    Additional
    0.10
     regarding
    0.09
     formatting
    0.09
    Remarks
    0.09
    Formatting
    0.09
    Act Density 0.034%

    No Known Activations