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

    Neuronpedia

    INDEX
    Explanations

    .com / github.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.98
     ০
    0.98
    ០
    0.95
    i
    0.94
     Giveen
    0.92
     ০৯
    0.88
     բ
    0.88
     는
    0.87
     Mạnh
    0.87
    𝟘
    0.87
    POSITIVE LOGITS
    1.58
    ו
    1.50
    ات
    1.38
    و
    1.37
    م
    1.12
    ل
    1.04
    ва
    1.02
    ور
    0.97
    رت
    0.96
    ින්
    0.95
    Act Density 0.000%

    No Known Activations