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

    Neuronpedia

    INDEX
    Explanations

    arithmetic calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ऑक्साइड
    1.48
    ⿵
    1.38
    து
    1.27
    ﺔ
    1.26
    oarthritis
    1.24
    ेंट
    1.23
    ₄
    1.23
     gerçekleşt
    1.22
    .}\
    1.21
    𝑨
    1.20
    POSITIVE LOGITS
     that
    1.17
     which
    1.16
    <0x99>
    1.06
    <0xA2>
    1.05
     the
    1.05
    ays
    1.04
     request
    1.04
    ă
    1.03
    ك
    1.02
    ments
    1.02
    Act Density 0.846%

    No Known Activations