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

    Neuronpedia

    INDEX
    Explanations

    obtain specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱐
    1.34
    ０
    1.30
    0
    1.19
    1.12
    ）；
    0.99
     沒有
    0.98
     važ
    0.96
    ことなく
    0.95
    ве
    0.93
     trycatch
    0.93
    POSITIVE LOGITS
    ก
    1.58
    ם
    1.52
    m
    1.49
    ן
    1.35
     on
    1.29
    ิ
    1.24
     it
    1.18
    ف
    1.18
    ↵
    1.17
    ной
    1.17
    Act Density 0.012%

    No Known Activations