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

    Neuronpedia

    INDEX
    Explanations

    expressing potential or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jeżeli
    0.40
     uważ
    0.40
     wenn
    0.40
     dbcontext
    0.39
     اگر
    0.38
     있다면
    0.38
     Probably
    0.38
     Coatings
    0.37
     probably
    0.36
    Wouldn
    0.36
    POSITIVE LOGITS
     either
    0.81
    either
    0.76
    anything
    0.74
     anything
    0.73
     berupa
    0.71
     либо
    0.71
    Either
    0.67
     entweder
    0.65
    Anything
    0.64
    可以是
    0.64
    Act Density 0.010%

    No Known Activations