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

    Neuronpedia

    INDEX
    Explanations

    Tribe, runtime, Drake, Flux

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    я
    3.26
    টি
    3.14
    اً
    3.08
    𝘦
    2.97
    ح
    2.96
    是最
    2.95
    𝘩
    2.87
    𝘵
    2.82
    دت
    2.80
    al
    2.77
    POSITIVE LOGITS
     Thankfully
    2.86
     milliliters
    2.85
     Fortunately
    2.79
     stateMutability
    2.73
     buckles
    2.63
    ्रिक
    2.63
    ‖</
    2.60
     nhắn
    2.59
    ర్‌లో
    2.58
    Fortunately
    2.58
    Act Density 0.096%

    No Known Activations