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

    Neuronpedia

    INDEX
    Explanations

    (s)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.73
    ూరు
    0.73
    特
    0.66
    パ
    0.66
    ၻ
    0.65
    イ
    0.65
    𝟯
    0.65
    カ
    0.64
    𝐩
    0.64
    砟
    0.64
    POSITIVE LOGITS
    ים
    0.86
    s
    0.73
     wares
    0.70
    <0x0D>
    0.70
    en
    0.68
    ти
    0.66
    ओं
    0.66
     đôi
    0.65
    வில்
    0.64
     (“
    0.63
    Act Density 0.006%

    No Known Activations