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

    Neuronpedia

    INDEX
    Explanations

    variations and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amplo
    0.86
     Excellent
    0.81
     Cham
    0.76
    },$
    0.73
     realizado
    0.72
     Excelente
    0.71
     основным
    0.71
    闿
    0.71
     excelente
    0.70
     descub
    0.70
    POSITIVE LOGITS
    hate
    0.78
    ца
    0.76
    ר
    0.73
    र
    0.73
    పాటు
    0.70
    少了
    0.70
    jquery
    0.69
    carte
    0.69
    竞赛
    0.69
    عه
    0.68
    Act Density 0.000%

    No Known Activations