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

    Neuronpedia

    INDEX
    Explanations

    unless or except

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     πολλ
    0.39
     لل
    0.38
     notamment
    0.38
     कई
    0.38
     हुँ
    0.38
     उपन्यास
    0.37
     зокрема
    0.37
     joka
    0.37
    ynthia
    0.37
     برای
    0.37
    POSITIVE LOGITS
     unless
    0.84
    unless
    0.66
     Unless
    0.64
    Unless
    0.59
     except
    0.54
    除非
    0.50
     excepting
    0.50
     Except
    0.49
    except
    0.47
     kecuali
    0.46
    Act Density 0.043%

    No Known Activations