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

    Neuronpedia

    INDEX
    Explanations

    国际

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reducers
    -0.08
    .reducer
    -0.08
    Reducers
    -0.08
     Müller
    -0.07
     decreases
    -0.07
    依
    -0.07
     définir
    -0.07
     Sex
    -0.07
    कर्ता
    -0.07
    isent
    -0.07
    POSITIVE LOGITS
     bbox
    0.09
     Buffalo
    0.09
     भिड
    0.09
     savvy
    0.08
     Liga
    0.08
     مسابق
    0.08
     تجهیز
    0.08
     конкурс
    0.08
     dubbed
    0.07
     turnaround
    0.07
    Act Density 0.017%

    No Known Activations