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

    Neuronpedia

    INDEX
    Explanations

    programming constructs definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    corrhi
    -1.24
    colgante
    -1.17
     pegatinas
    -1.13
    Fonto
    -1.09
     capuz
    -1.09
     algodão
    -1.09
     quedaron
    -1.08
    consejos
    -1.08
     schuldig
    -1.07
    ὢ
    -1.07
    POSITIVE LOGITS
     to
    0.94
    されていました
    0.93
     can
    0.93
    って思
    0.91
     last
    0.90
     czerwca
    0.86
    風味
    0.86
     as
    0.85
     lipca
    0.85
     kwietnia
    0.85
    Act Density 0.008%

    No Known Activations