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

    Neuronpedia

    INDEX
    Explanations

    języ, obserw, notować, mnożenie, Warszawy, niedziela, książka

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dessa
    0.64
     Pokud
    0.63
     velmi
    0.61
     zcela
    0.60
     Dacă
    0.60
     veľmi
    0.59
     Mentre
    0.59
     Dopo
    0.57
     vozila
    0.57
     Так
    0.56
    POSITIVE LOGITS
     contingent
    0.47
     competent
    0.46
     cumbersome
    0.45
    ченный
    0.44
     encroach
    0.41
     everyday
    0.40
     willingness
    0.39
     inter
    0.39
     portfolio
    0.39
     forward
    0.38
    Act Density 0.004%

    No Known Activations