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

    Neuronpedia

    INDEX
    Explanations

    beneficial or detrimental

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    40
    -0.06
     vortex
    -0.06
     Ignore
    -0.06
     Thesis
    -0.06
    ovation
    -0.06
    支付
    -0.06
     jaar
    -0.06
    _lambda
    -0.06
    \r
    -0.06
     Harmony
    -0.06
    POSITIVE LOGITS
     IRC
    0.06
    /trunk
    0.06
     bilg
    0.06
    -nil
    0.06
     SELECT
    0.06
    ọi
    0.06
    北市
    0.06
    	SELECT
    0.06
    FROM
    0.06
     reminiscent
    0.06
    Act Density 0.179%

    No Known Activations