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

    Neuronpedia

    INDEX
    Explanations

    code blocks or function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    り
    1.10
    ிறது
    1.05
    да
    0.95
    i
    0.94
    ை
    0.93
    ે
    0.93
    theless
    0.93
    oretically
    0.90
    ছেন
    0.88
    া
    0.88
    POSITIVE LOGITS
    কে
    0.86
    ер
    0.85
    на
    0.80
    toon
    0.80
    neſs
    0.80
     lượng
    0.78
    AsyncKeyState
    0.77
    を手
    0.77
     juara
    0.77
     ومع
    0.75
    Act Density 0.165%

    No Known Activations