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

    Neuronpedia

    INDEX
    Explanations

    decision before choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.53
     rules
    0.52
     '
    0.51
     leader
    0.51
     -
    0.50
     language
    0.50
     plume
    0.50
     legado
    0.48
    z
    0.47
     word
    0.47
    POSITIVE LOGITS
     செல்சிய
    0.57
    larına
    0.56
    Ｃ
    0.56
     கெல்
    0.54
    砒
    0.54
    युक्त
    0.53
    LookAnd
    0.53
    dataPro
    0.53
     LongNumber
    0.52
    idcoin
    0.51
    Act Density 0.000%

    No Known Activations