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

    Neuronpedia

    INDEX
    Explanations

    Win followed by disabled/Win

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.56
     og
    0.43
    ina
    0.43
    য়ার
    0.43
    ’
    0.43
    \
    0.40
    の
    0.40
    가
    0.40
    ∞</
    0.40
    นิยม
    0.39
    POSITIVE LOGITS
     tapestry
    0.50
     keypad
    0.46
     hence
    0.44
     vgl
    0.44
    _;
    0.44
     cd
    0.43
     Bhat
    0.43
     seide
    0.42
    ;//
    0.42
     همچنین
    0.42
    Act Density 0.005%

    No Known Activations