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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	type
    -0.07
    ============↵
    -0.07
    екс
    -0.06
    这个时代
    -0.06
    >({↵
    -0.06
    _factors
    -0.06
    ˡ
    -0.06
    唉
    -0.06
    假如
    -0.06
     vow
    -0.06
    POSITIVE LOGITS
    屯
    0.08
    ﳒ
    0.07
    și
    0.07
     Carroll
    0.07
     UNSIGNED
    0.07
    igu
    0.07
     Alternate
    0.07
    되어
    0.07
    CTSTR
    0.06
     soluble
    0.06
    Act Density 0.013%

    No Known Activations