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

    Neuronpedia

    INDEX
    Explanations

    divisors, remainders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     πλη
    -0.07
     مض
    -0.06
     aime
    -0.06
    OWL
    -0.06
     به
    -0.06
    role
    -0.06
    Var
    -0.06
     eligibility
    -0.06
    .exp
    -0.06
     hava
    -0.06
    POSITIVE LOGITS
    ↵    ↵↵
    0.07
    ↵↵↵↵↵↵
    0.07
     خوبی
    0.06
    cip
    0.06
    )↵↵↵↵↵↵↵↵
    0.06
    략
    0.06
     майже
    0.06
     ningún
    0.06
    	Return
    0.06
     sağlayan
    0.06
    Act Density 0.011%

    No Known Activations