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

    Neuronpedia

    INDEX
    Explanations

    methodology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    conference
    -0.07
     slit
    -0.07
     unserer
    -0.06
     integrated
    -0.06
    -associated
    -0.06
     Fighters
    -0.06
    community
    -0.06
     modification
    -0.06
     Π
    -0.06
    -0.06
    POSITIVE LOGITS
     ham
    0.07
    ELSE
    0.06
    351
    0.06
    ailing
    0.06
    IEnumerator
    0.06
     sebe
    0.06
     proverb
    0.06
    uper
    0.06
     раст
    0.06
    اسیون
    0.06
    Act Density 0.039%

    No Known Activations