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

    Neuronpedia

    INDEX
    Explanations

    in and around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kemudian
    1.30
    𝒕
    1.28
    ⓪
    1.26
    1.23
    敚
    1.19
    ων
    1.18
     层
    1.18
     zejména
    1.17
    ქ
    1.17
     fleste
    1.16
    POSITIVE LOGITS
    or
    1.49
    le
    1.45
    i
    1.38
    2
    1.36
     mocks
    1.35
     a
    1.34
    ans
    1.34
    ah
    1.31
    aw
    1.31
     researches
    1.31
    Act Density 0.000%

    No Known Activations