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

    Neuronpedia

    INDEX
    Explanations

    knees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사
    0.76
     இந்து
    0.76
    provider
    0.74
     sheer
    0.73
     `
    0.71
    ↵
    0.71
     compelling
    0.69
    mental
    0.69
    ల్యే
    0.69
    companies
    0.68
    POSITIVE LOGITS
    gür
    0.99
    ث
    0.93
    ى
    0.90
    ст
    0.87
     samoglas
    0.86
    ви
    0.86
     thự
    0.86
    ف
    0.86
    짙
    0.86
     entrees
    0.86
    Act Density 0.003%

    No Known Activations