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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and attributes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	in
    -0.07
     methodology
    -0.07
     verilen
    -0.07
     chang
    -0.07
    _DSP
    -0.06
    勇
    -0.06
    _and
    -0.06
    ONE
    -0.06
     allele
    -0.06
    _hor
    -0.06
    POSITIVE LOGITS
    업
    0.07
     bundled
    0.06
    poster
    0.06
    _FALSE
    0.06
     coordination
    0.06
     Bankası
    0.06
    นวย
    0.06
    arakter
    0.06
     компон
    0.06
    INCREMENT
    0.05
    Act Density 0.048%

    No Known Activations