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

    Neuronpedia

    INDEX
    Explanations

    Google or traffic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    եր
    0.40
    ಲಿಯ
    0.39
    文書
    0.38
     errone
    0.38
     misfortunes
    0.38
    θρω
    0.37
     परीक्ष
    0.37
    顶点
    0.36
     pancake
    0.36
    عرف
    0.36
    POSITIVE LOGITS
     IEEE
    0.38
     basadas
    0.37
    fir
    0.36
     dian
    0.35
    łasz
    0.35
     সাস
    0.35
    radeon
    0.35
     склада
    0.35
     فيها
    0.34
    斯坦
    0.34
    Act Density 0.000%

    No Known Activations