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

    Neuronpedia

    INDEX
    Explanations

    mistakes and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    哃
    0.39
     એન
    0.39
    сун
    0.38
    yleg
    0.37
    uria
    0.34
    症状
    0.33
    PIRE
    0.33
    ுறு
    0.33
    ència
    0.33
    loom
    0.32
    POSITIVE LOGITS
     mistakes
    2.33
     Mistakes
    2.06
     mistake
    2.05
     errors
    1.92
     kesalahan
    1.84
    错误
    1.80
     erreurs
    1.77
     errores
    1.76
     Fehler
    1.75
     ошибок
    1.74
    Act Density 0.027%

    No Known Activations