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

    Neuronpedia

    INDEX
    Explanations

    word then of or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     May
    0.16
    :
    0.16
    và
    0.16
    s
    0.16
    ;
    0.16
    ,
    0.16
    <b>
    0.16
     niego
    0.16
    V
    0.16
    ↵↵
    0.15
    POSITIVE LOGITS
     של
    0.25
     of
    0.25
    នៃ
    0.21
     विभिन्न
    0.21
     ከ
    0.21
     വിവിധ
    0.21
    䏹
    0.20
     उन
    0.20
    了他的
    0.20
    <unused2171>
    0.20
    Act Density 0.181%

    No Known Activations