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

    Neuronpedia

    INDEX
    Explanations

    informational texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ablauf
    -0.09
     Taller
    -0.07
    Eff
    -0.07
     Defense
    -0.07
     Singleton
    -0.07
     Expanded
    -0.07
    ŵ
    -0.07
    winds
    -0.07
    court
    -0.07
     Giving
    -0.07
    POSITIVE LOGITS
     얼마나
    0.11
     कित
    0.11
     কত
    0.10
     ఎంత
    0.10
     कितना
    0.10
     vezes
    0.09
     насколько
    0.09
     combien
    0.09
     cuánto
    0.09
    多少
    0.09
    Act Density 0.089%

    No Known Activations