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

    Neuronpedia

    INDEX
    Explanations

    programming code and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     އި
    0.36
    oblasts
    0.35
     ت
    0.34
     开始
    0.33
     גי
    0.33
    franz
    0.32
    丽
    0.32
     ثلاثة
    0.32
    rière
    0.32
     purpure
    0.32
    POSITIVE LOGITS
     deten
    0.34
    因
    0.33
     VCO
    0.32
    هم
    0.32
     Alguns
    0.32
     Apesar
    0.31
    就是
    0.31
     assertEquals
    0.31
    テム
    0.31
     Podczas
    0.30
    Act Density 0.015%

    No Known Activations