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

    Neuronpedia

    INDEX
    Explanations

    Elon Musk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.70
    ری
    0.70
    ী
    0.64
    Điều
    0.60
    рино
    0.59
    ی
    0.59
    起
    0.58
    好
    0.58
    ای
    0.57
     OutputStream
    0.57
    POSITIVE LOGITS
     topic
    0.62
     नमस्कार
    0.61
     vean
    0.59
    ienst
    0.59
     consecut
    0.58
    ཋ
    0.56
     continuation
    0.55
     지난해
    0.55
     tactic
    0.54
     보겠습니다
    0.54
    Act Density 0.000%

    No Known Activations