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

    Neuronpedia

    INDEX
    Explanations

    intended for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಾರ
    0.47
    を確認
    0.46
    adillo
    0.46
    ರೀ
    0.44
    ಶಸ್
    0.43
    กรรม
    0.43
    ಗೆ
    0.41
    டம்
    0.41
    ଷ
    0.41
    あり
    0.41
    POSITIVE LOGITS
     In
    0.44
    EN
    0.43
     Fell
    0.43
     落
    0.42
     موسم
    0.41
     Putra
    0.41
    **:
    0.41
     Tags
    0.40
     Ecol
    0.40
    (
    0.40
    Act Density 0.001%

    No Known Activations