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

    Neuronpedia

    INDEX
    Explanations

    。

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    राबरी
    0.73
     referenced
    0.72
     boldly
    0.71
     rated
    0.69
     dành
    0.68
    andom
    0.67
     named
    0.65
    への
    0.64
     totaling
    0.64
     lowercase
    0.64
    POSITIVE LOGITS
    。
    1.53
    。(
    1.30
    ।
    1.29
    。“
    1.20
    。「
    1.20
    。"
    1.16
    。\
    1.12
    ։
    1.11
    ።
    1.10
    。（
    1.09
    Act Density 0.034%

    No Known Activations