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

    Neuronpedia

    INDEX
    Explanations

    AI stories and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وع
    0.49
     samples
    0.46
     örnek
    0.44
     bilgis
    0.43
     wereld
    0.43
    mys
    0.42
     modernen
    0.42
     वैज्ञानिकों
    0.41
     kullanılır
    0.41
     ejemplo
    0.41
    POSITIVE LOGITS
    㓞
    0.47
    各项
    0.42
    }"]
    0.40
     MDET
    0.40
    各种
    0.38
    謨
    0.38
     Initial
    0.38
    之时
    0.38
    "...
    0.38
    Initial
    0.37
    Act Density 0.001%

    No Known Activations