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

    Neuronpedia

    INDEX
    Explanations

    HTML lists and tabs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pagination
    -0.06
    uctor
    -0.06
    Dead
    -0.06
     Translator
    -0.06
     throat
    -0.06
    renderer
    -0.06
    动物
    -0.06
    National
    -0.06
    .did
    -0.06
     ATK
    -0.06
    POSITIVE LOGITS
     bogus
    0.08
    uebas
    0.07
     الاح
    0.07
    _Dis
    0.07
    ‌شوند
    0.07
     �
    0.07
    uther
    0.06
     編
    0.06
     UV
    0.06
    (outputs
    0.06
    Act Density 0.006%

    No Known Activations