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

    Neuronpedia

    INDEX
    Explanations

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Situation
    -0.09
     apparently
    -0.08
     reportedly
    -0.08
     same
    -0.08
     Hack
    -0.08
     evidently
    -0.07
     также
    -0.07
     gleichen
    -0.07
     parehong
    -0.07
     Delta
    -0.07
    POSITIVE LOGITS
     מחדש
    0.09
    ishingiz
    0.09
    oloogia
    0.09
    atsiooni
    0.08
    sched
    0.08
    ಿಂಗ
    0.08
    的
    0.08
    રને
    0.08
    ರನ್ನು
    0.08
    's
    0.08
    Act Density 0.005%

    No Known Activations