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

    Neuronpedia

    INDEX
    Explanations

    break statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aplatis
    1.52
     iż
    1.41
     aquesta
    1.38
     enseign
    1.38
     humaines
    1.38
     concep
    1.36
     faç
    1.34
    ﺑ
    1.33
    мі
    1.32
    सी
    1.30
    POSITIVE LOGITS
     परंतु
    1.34
    platz
    1.23
    waffe
    1.20
     просмотра
    1.20
     السكان
    1.17
    Sx
    1.17
    ্কার
    1.16
    ums
    1.14
    AZ
    1.13
    ժ
    1.13
    Act Density 0.039%

    No Known Activations