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

    Neuronpedia

    INDEX
    Explanations

    must be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ☜
    1.26
    魍
    1.23
    𝒏
    1.22
     sdx
    1.18
    งาม
    1.17
    𝗻
    1.17
    ק
    1.16
    𝒄
    1.15
     absurdity
    1.14
    ्राफी
    1.13
    POSITIVE LOGITS
    и
    1.23
    要在
    1.17
    要做
    1.15
    ا
    1.12
    d
    1.09
    臾
    1.09
    s
    1.08
    Để
    1.06
    要有
    1.04
    Н
    1.04
    Act Density 0.120%

    No Known Activations