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

    Neuronpedia

    INDEX
    Explanations

    percentages and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RO
    0.25
    4
    0.23
    3
    0.23
     acquainted
    0.23
    Roz
    0.23
    5
    0.23
    ULATIONS
    0.22
     Cách
    0.22
    ):\
    0.22
    Inode
    0.21
    POSITIVE LOGITS
     in
    0.27
    咾
    0.25
    ↵
    0.25
     വരെ
    0.24
     but
    0.24
    त
    0.23
    ).
    0.23
     fordi
    0.23
    ！
    0.23
    ″
    0.23
    Act Density 0.157%

    No Known Activations