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

    Neuronpedia

    INDEX
    Explanations

    website/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apellido
    -0.07
    .assertEquals
    -0.07
     rezerv
    -0.07
     grenade
    -0.06
     فارس
    -0.06
     Raphael
    -0.06
    _RA
    -0.06
     nemoc
    -0.06
    oving
    -0.06
     Bài
    -0.06
    POSITIVE LOGITS
     loại
    0.06
     instagram
    0.06
     unlaw
    0.06
    ious
    0.06
     тов
    0.06
    >()↵↵
    0.06
    ?↵↵↵
    0.06
     mixer
    0.06
     excited
    0.06
    ↵   ↵
    0.06
    Act Density 0.000%

    No Known Activations