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

    Neuronpedia

    INDEX
    Explanations

    diverse platforms and improved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kuro
    0.39
    rante
    0.37
     sliders
    0.37
    ුවේ
    0.37
     চলমান
    0.36
     dolgo
    0.36
     onBackPressed
    0.36
     Db
    0.35
    माण
    0.35
    कस
    0.35
    POSITIVE LOGITS
    кси
    0.39
    សា
    0.39
    REND
    0.38
    एचओ
    0.38
    𝓎
    0.38
    类
    0.37
    шель
    0.37
    unjukan
    0.37
    所示
    0.36
    ில்லியன்
    0.36
    Act Density 0.000%

    No Known Activations