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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ρώ
    -0.06
    ци
    -0.06
    -Smith
    -0.06
    Pull
    -0.06
    หว
    -0.06
     Dawson
    -0.06
    board
    -0.06
    extern
    -0.06
     ฉ
    -0.06
    げ
    -0.06
    POSITIVE LOGITS
    onomy
    0.07
     togg
    0.06
    _REGEX
    0.06
     vener
    0.06
     placer
    0.06
     skilled
    0.06
     Katy
    0.06
     setSelected
    0.06
    [this
    0.06
     мої
    0.06
    Act Density 0.002%

    No Known Activations