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

    Neuronpedia

    INDEX
    Explanations

    Security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Defined
    -0.07
    Duplicates
    -0.06
     sto
    -0.06
    Simple
    -0.06
    .shuffle
    -0.06
     strips
    -0.06
     pronunciation
    -0.06
     crust
    -0.06
    new
    -0.06
     cancer
    -0.06
    POSITIVE LOGITS
    (Font
    0.07
    [jj
    0.07
     Teddy
    0.06
    \models
    0.06
    لع
    0.06
    untime
    0.06
    enties
    0.06
    .FromArgb
    0.06
    _PERIOD
    0.06
    óg
    0.06
    Act Density 0.015%

    No Known Activations