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

    Neuronpedia

    INDEX
    Explanations

    say "201" prefix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _load
    -0.07
    !",
    -0.07
    ;.
    -0.07
    udiante
    -0.07
    ;
    -0.07
    UIT
    -0.07
    uit
    -0.07
    West
    -0.07
    rial
    -0.06
     TERM
    -0.06
    POSITIVE LOGITS
     Fran
    0.06
     هذا
    0.06
     ادامه
    0.06
    \Migration
    0.06
     Ernst
    0.06
     Infect
    0.06
    .ListBox
    0.06
    Isn
    0.06
     Denis
    0.06
     Princip
    0.06
    Act Density 0.001%

    No Known Activations