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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ником
    -0.09
     greenhouse
    -0.08
     учетом
    -0.08
    çisi
    -0.08
     policeman
    -0.08
    никами
    -0.08
    خصوص
    -0.08
     weighing
    -0.07
    Так
    -0.07
     pratiquer
    -0.07
    POSITIVE LOGITS
     Propel
    0.09
    ズ
    0.08
    0.08
     தொடர்ப
    0.08
     swapping
    0.07
     Mata
    0.07
     dolls
    0.07
     Inspire
    0.07
     débat
    0.07
     Debit
    0.07
    Act Density 0.007%
    No Known Activations