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

    Neuronpedia

    INDEX
    Explanations

    reporting dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ও
    0.34
     ...)
    0.33
     +
    0.32
     \&
    0.31
     \)
    0.31
    比較的
    0.30
    ებულია
    0.29
    नाची
    0.29
     and
    0.29
    および
    0.29
    POSITIVE LOGITS
    。
    0.53
    ۔
    0.46
    ።
    0.42
    ။
    0.41
    ،
    0.39
    ।
    0.39
    。《
    0.38
    ។
    0.38
    紝
    0.35
    rneğin
    0.34
    Act Density 0.007%

    No Known Activations