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

    Neuronpedia

    INDEX
    Explanations

    Statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plentiful
    -0.07
    avers
    -0.07
    Missing
    -0.07
     мати
    -0.06
    YYYY
    -0.06
     lovers
    -0.06
    (curr
    -0.06
    _inst
    -0.06
     masters
    -0.06
     Python
    -0.06
    POSITIVE LOGITS
    ´
    0.07
    wcsstore
    0.07
     мен
    0.07
    da
    0.07
    //:
    0.07
     ´
    0.06
    /dev
    0.06
    -word
    0.06
     pea
    0.06
    otional
    0.06
    Act Density 0.046%

    No Known Activations