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

    Neuronpedia

    INDEX
    Explanations

    specific + descriptive noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     फट
    1.20
    ட்கள்
    1.19
     pioneering
    1.17
     soaring
    1.17
     courageous
    1.16
    atet
    1.14
    부터
    1.13
    ろう
    1.13
     wę
    1.13
     sabiduría
    1.11
    POSITIVE LOGITS
    ures
    1.47
    maire
    1.38
     Objet
    1.37
    laut
    1.37
    ifies
    1.35
    $)
    1.35
    name
    1.33
    ف
    1.33
    NAME
    1.32
    bentuk
    1.31
    Act Density 0.100%

    No Known Activations