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

    Neuronpedia

    INDEX
    Explanations

    authorized by an entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.69
     expand
    0.64
     mingle
    0.64
    ó
    0.63
    ')]
    0.58
     infuse
    0.58
     valoración
    0.58
    说
    0.57
    ');
    0.56
     disperse
    0.56
    POSITIVE LOGITS
    도
    0.64
     Pemerintah
    0.57
    kommer
    0.55
    ވެ
    0.53
     আদালতের
    0.52
     किंवा
    0.51
     운
    0.51
    スタ
    0.51
     Ovaj
    0.51
    も
    0.50
    Act Density 0.022%

    No Known Activations