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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zorgen
    -0.09
    alex
    -0.08
    ಿಸಿದ್ದರು
    -0.08
     battle
    -0.08
     envolvendo
    -0.08
    ilem
    -0.07
     Miracle
    -0.07
    ohon
    -0.07
    ულის
    -0.07
    -Go
    -0.07
    POSITIVE LOGITS
    (updated
    0.10
    Updated
    0.09
    UPDATED
    0.09
    _updated
    0.09
    updated
    0.09
    .updated
    0.09
     updated
    0.08
     Updated
    0.08
     అదే
    0.08
    ke
    0.08
    Act Density 0.133%

    No Known Activations