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

    Neuronpedia

    INDEX
    Explanations

    writing sales copy outlining benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otch
    0.47
    видно
    0.45
    Dans
    0.44
    Vous
    0.44
    你
    0.43
    Sum
    0.43
    ائیں۔
    0.42
    ো
    0.41
    お
    0.40
     кто
    0.40
    POSITIVE LOGITS
     formul
    0.48
     katth
    0.48
     factual
    0.47
     wasser
    0.47
     ín
    0.46
    เส
    0.46
     Preface
    0.46
    ipennis
    0.45
     Rhin
    0.45
     bằng
    0.45
    Act Density 0.000%

    No Known Activations