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

    Neuronpedia

    INDEX
    Explanations

    celestia or extended essay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.45
    ↵
    1.43
    e
    1.41
    a
    1.30
    i
    1.28
    :
    1.27
     TV
    1.26
     EU
    1.24
     CPU
    1.18
     PC
    1.17
    POSITIVE LOGITS
    е
    1.51
    ع
    1.48
    ж
    1.38
    لي
    1.32
    í
    1.32
    ц
    1.32
    ха
    1.31
    х
    1.30
    ε
    1.30
    де
    1.29
    Act Density 0.000%

    No Known Activations