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

    Neuronpedia

    INDEX
    Explanations

    hundredths place

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mitar
    -0.08
     Nigel
    -0.08
     تناول
    -0.08
    ően
    -0.08
     老
    -0.08
    ъч
    -0.08
    -0.08
    ikkert
    -0.08
    ण्यात
    -0.08
    老师
    -0.07
    POSITIVE LOGITS
    fraction
    0.09
    voud
    0.09
    grand
    0.09
     thousand
    0.08
    trip
    0.08
     subse
    0.08
    glass
    0.08
     fractions
    0.08
    units
    0.08
    fract
    0.08
    Act Density 0.007%
    No Known Activations