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

    Neuronpedia

    INDEX
    Explanations

    condition or temporal clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    裡的
    0.43
     Being
    0.42
     быть
    0.41
    Being
    0.41
     Harlem
    0.39
     Toronto
    0.39
     wits
    0.39
    মধ্যে
    0.38
    __.__
    0.38
     Strath
    0.37
    POSITIVE LOGITS
     når
    0.63
     when
    0.59
     gdy
    0.55
     apenas
    0.53
     när
    0.52
     ஏற்படும்
    0.52
    when
    0.51
     yalnızca
    0.51
    cuando
    0.51
     if
    0.50
    Act Density 0.000%

    No Known Activations