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

    Neuronpedia

    INDEX
    Explanations

    RAINN organization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    κες
    0.92
     telef
    0.92
    cron
    0.89
    ﻧ
    0.88
     overheating
    0.87
    সমূহ
    0.86
     ಹೊ
    0.85
     mostr
    0.85
     east
    0.84
    cohol
    0.84
    POSITIVE LOGITS
     thuận
    0.92
     cher
    0.82
    र्मेंद्र
    0.81
     ক্রী
    0.78
     сфор
    0.77
    citealt
    0.75
    boots
    0.74
     বিঘ
    0.74
    seur
    0.74
    סי
    0.73
    Act Density 0.109%

    No Known Activations