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

    Neuronpedia

    INDEX
    Explanations

    hypothesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pady
    -0.06
    佐
    -0.06
    _grad
    -0.06
    Collection
    -0.06
     ANAL
    -0.06
     poultry
    -0.06
     awards
    -0.06
    dictions
    -0.06
     buyers
    -0.06
     shoppers
    -0.06
    POSITIVE LOGITS
     Aş
    0.07
    (hash
    0.07
    няют
    0.07
    stile
    0.06
     Napoli
    0.06
     blatantly
    0.06
     Weinstein
    0.06
    альна
    0.06
     contestant
    0.06
     refuses
    0.06
    Act Density 0.014%

    No Known Activations