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

    Neuronpedia

    INDEX
    Explanations

    except / try except blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সন্
    0.38
    ➹
    0.37
    轶
    0.36
     og
    0.36
     yandan
    0.36
    قد
    0.33
    criteria
    0.33
     محدود
    0.33
     volledig
    0.33
    ഢ
    0.33
    POSITIVE LOGITS
     except
    2.28
    except
    2.17
     Except
    2.05
    Except
    2.00
     excepto
    1.78
     kecuali
    1.77
     EXCEPT
    1.65
     sauf
    1.61
     excepting
    1.48
    除
    1.43
    Act Density 0.049%

    No Known Activations