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

    Neuronpedia

    INDEX
    Explanations

    latex math alignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ತಕ್ಕ
    0.42
    otyping
    0.42
     valorem
    0.39
    ारण
    0.39
    ustible
    0.39
     KC
    0.39
     Fc
    0.38
    evident
    0.38
     raid
    0.38
     natura
    0.38
    POSITIVE LOGITS
    初始化
    0.40
     注
    0.40
    isPrime
    0.40
    罗
    0.40
    ล
    0.39
    地
    0.39
    ungkinan
    0.39
    িল
    0.38
    mathcal
    0.38
    ेल
    0.38
    Act Density 0.001%

    No Known Activations