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

    Neuronpedia

    INDEX
    Explanations

    contrasting similarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fil
    0.41
     metastable
    0.37
    일까지
    0.35
     bargain
    0.35
     Barg
    0.34
     tergantung
    0.34
    薬品
    0.34
     antaranya
    0.34
     باید
    0.34
    aldi
    0.33
    POSITIVE LOGITS
     except
    1.03
     Except
    0.94
    只不过
    0.93
    except
    0.92
    Except
    0.87
     excepto
    0.82
     ولكن
    0.77
     minus
    0.76
     EXCEPT
    0.75
     but
    0.73
    Act Density 0.157%

    No Known Activations