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

    Neuronpedia

    INDEX
    Explanations

    . this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jakieś
    0.63
     soms
    0.61
     nogen
    0.60
     họ
    0.59
    他們
    0.59
     einige
    0.59
     вони
    0.59
     blobs
    0.59
     nějak
    0.58
    他们
    0.58
    POSITIVE LOGITS
     Despite
    0.74
     Furthermore
    0.73
     despite
    0.67
    Furthermore
    0.66
    Despite
    0.64
    cknowled
    0.64
     Moreover
    0.59
    despite
    0.57
     Therefore
    0.57
    while
    0.55
    Act Density 0.062%

    No Known Activations