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

    Neuronpedia

    INDEX
    Explanations

    il

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Disallow
    -0.07
     await
    -0.06
    opus
    -0.06
     brows
    -0.06
    _NEXT
    -0.06
     addicted
    -0.06
    .Errorf
    -0.06
    orph
    -0.06
    /
↵
↵
    -0.06
     unify
    -0.06
    POSITIVE LOGITS
    �
    0.07
     技
    0.07
     Esp
    0.06
     sách
    0.06
     Cherokee
    0.06
     Toilet
    0.06
     Giới
    0.06
     Mog
    0.06
     abusing
    0.06
    apanese
    0.06
    Act Density 0.000%

    No Known Activations