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

    Neuronpedia

    INDEX
    Explanations

    rewording suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াট
    0.43
     not
    0.42
     couche
    0.39
    2
    0.39
     permiten
    0.39
    кович
    0.38
     mètres
    0.38
     appren
    0.38
     prenot
    0.38
    ateau
    0.38
    POSITIVE LOGITS
     போய்
    0.38
    㻴
    0.37
     낙
    0.36
     가지
    0.35
     ಒ
    0.35
     தீங்கு
    0.35
     inferiority
    0.35
     다섯
    0.35
    䪲
    0.35
    墂
    0.34
    Act Density 0.060%

    No Known Activations