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

    Neuronpedia

    INDEX
    Explanations

    formula$$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alamy
    0.54
     antisymmetric
    0.53
     menik
    0.51
    囵
    0.50
    により
    0.50
     pecinta
    0.49
    Ꮘ
    0.49
     vaid
    0.49
     JG
    0.49
    يميديا
    0.49
    POSITIVE LOGITS
    Formula
    0.67
    \[
    0.63
     Formula
    0.57
     formula
    0.49
     replay
    0.49
    replay
    0.47
    repl
    0.47
    Till
    0.46
    formula
    0.46
    $$
    0.45
    Act Density 0.000%

    No Known Activations