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

    Neuronpedia

    INDEX
    Explanations

    professional sign-offs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    1.31
    OS
    1.23
    苓
    1.21
    icca
    1.15
    冇
    1.15
     innervation
    1.12
    ing
    1.11
     основу
    1.11
    而是
    1.08
    含量
    1.08
    POSITIVE LOGITS
    s
    1.51
    เจน
    1.25
    />
    1.20
    های
    1.19
    点了点头
    1.18
    mselves
    1.16
    ਰ
    1.15
    א
    1.13
    di
    1.12
     andra
    1.12
    Act Density 0.004%

    No Known Activations