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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    paa
    -0.09
    ऊन
    -0.09
     مراسم
    -0.09
     مسب
    -0.08
    ühm
    -0.08
     hablar
    -0.08
     पूजा
    -0.08
     قبض
    -0.08
    казать
    -0.08
     parlent
    -0.08
    POSITIVE LOGITS
     comprises
    0.07
     comprised
    0.07
     calculation
    0.07
     הכול
    0.07
     nostru
    0.07
     mů
    0.07
    -form
    0.07
     Received
    0.07
     blond
    0.07
     kil
    0.07
    Act Density 0.055%

    No Known Activations