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

    Neuronpedia

    INDEX
    Explanations

    .com and .io domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pampered
    0.21
     OKC
    0.19
     hammered
    0.19
     are
    0.19
    Firebase
    0.18
     numerosi
    0.18
    <0x91>
    0.18
     المركز
    0.18
    奋
    0.18
     którzy
    0.17
    POSITIVE LOGITS
    션
    0.23
    of
    0.22
    z
    0.22
    x
    0.21
    зо
    0.20
    ể
    0.20
    ból
    0.20
    ing
    0.19
    cios
    0.19
    væ
    0.19
    Act Density 0.000%

    No Known Activations