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

    Neuronpedia

    INDEX
    Explanations

    technical computing terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     গুলো
    0.50
     restantes
    0.47
     uur
    0.45
     Auswirkungen
    0.45
    ার্থীরা
    0.44
     Essence
    0.44
     первые
    0.44
     any
    0.44
     исти
    0.43
     Starbucks
    0.43
    POSITIVE LOGITS
     whose
    0.66
     რომელიც
    0.63
     with
    0.61
    和一个
    0.60
     که
    0.59
     of
    0.58
     from
    0.57
     that
    0.57
     thats
    0.57
     cuya
    0.57
    Act Density 0.315%

    No Known Activations