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

    Neuronpedia

    INDEX
    Explanations

    complementary pairs or combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     The
    -3.81
     avec
    -2.95
     WITH
    -2.91
    *}[
    -2.41
     当
    -2.39
    thschild
    -2.39
     Your
    -2.34
     -
    -2.31
     A
    -2.30
     With
    -2.28
    POSITIVE LOGITS
    骜
    3.19
     parachoque
    3.09
    棪
    3.03
    眎
    3.02
    橚
    3.00
    鐿
    2.84
    芣
    2.84
    ୌ
    2.83
     墊
    2.80
    ization
    2.78
    Act Density 0.007%

    No Known Activations