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

    Neuronpedia

    INDEX
    Explanations

    parentheses or quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ขาด
    -0.07
    .people
    -0.07
    تحض
    -0.07
    .pat
    -0.07
    .Cho
    -0.07
     다음과
    -0.07
    Ԉ
    -0.06
    没
    -0.06
     لو
    -0.06
    _JS
    -0.06
    POSITIVE LOGITS
    自律
    0.07
    abyte
    0.07
    nte
    0.07
     opponent
    0.07
    setVisible
    0.07
    ائك
    0.07
    (enemy
    0.06
     friendly
    0.06
    orrent
    0.06
     grinder
    0.06
    Act Density 0.003%

    No Known Activations