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

    Neuronpedia

    INDEX
    Explanations

    year over year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sekali
    0.90
    ^{-}
    0.87
     prokary
    0.87
     राज्यों
    0.86
    ্ভব
    0.86
    ❤❤
    0.82
    𝟐
    0.81
    ⸱
    0.81
    úly
    0.80
    movies
    0.79
    POSITIVE LOGITS
    ↵
    1.19
    ach
    1.05
    ad
    0.89
    apping
    0.87
    ف
    0.86
    ast
    0.82
    ق
    0.82
     Federation
    0.81
    ске
    0.80
    ोन
    0.79
    Act Density 0.000%

    No Known Activations