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

    Neuronpedia

    INDEX
    Explanations

    date picker or math fraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ѡ
    0.40
     conductors
    0.39
    Coords
    0.39
     discrimin
    0.38
     Sementara
    0.38
    ்ட
    0.38
    lecht
    0.38
    amantha
    0.38
     clearances
    0.38
     አመ
    0.38
    POSITIVE LOGITS
     setData
    0.40
     трёх
    0.39
    跨
    0.38
     allow
    0.38
     undefined
    0.37
    一块
    0.36
    唱歌
    0.36
    立て
    0.36
     (…)
    0.36
    便捷
    0.35
    Act Density 0.000%

    No Known Activations