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

    Neuronpedia

    INDEX
    Explanations

    built and secrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    0.42
    ்
    0.39
    可以看出
    0.35
    یل
    0.34
    ↵
    0.31
    ov
    0.30
    ‍
    0.30
    ↵↵
    0.30
    াউ
    0.29
    k
    0.29
    POSITIVE LOGITS
    ھیں
    0.38
     solutes
    0.38
    𝘵
    0.37
    ियल
    0.37
    竰
    0.37
    <unused1877>
    0.37
     Workmen
    0.36
    <unused697>
    0.35
     rctx
    0.35
    𝘤
    0.35
    Act Density 0.294%

    No Known Activations