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

    Neuronpedia

    INDEX
    Explanations

    structured text headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Self
    0.47
     सेल्फ
    0.44
    ₁)
    0.41
    destroyEach
    0.41
     Self
    0.40
    不允许
    0.40
    Lindsay
    0.38
     метал
    0.38
    acchus
    0.38
    दछ
    0.38
    POSITIVE LOGITS
     cel
    0.47
     যোগ্য
    0.47
     distressed
    0.44
     origami
    0.44
     more
    0.41
     entorno
    0.41
     voorzien
    0.41
     profil
    0.40
     lesbian
    0.40
     Ivory
    0.40
    Act Density 0.002%

    No Known Activations