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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ella
    -0.07
     Wil
    -0.07
     persuaded
    -0.07
    $v
    -0.06
     CEL
    -0.06
     Prote
    -0.06
    serialization
    -0.06
     giveaway
    -0.06
    matched
    -0.06
    Cube
    -0.06
    POSITIVE LOGITS
    acific
    0.07
     ukáz
    0.06
     cinsel
    0.06
    ทำงาน
    0.06
     kategor
    0.06
    .GetEnumerator
    0.06
    Важ
    0.06
     mụn
    0.06
     geldi
    0.06
    敏
    0.06
    Act Density 0.051%

    No Known Activations