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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	sum
    -0.07
     edilir
    -0.06
     Sao
    -0.06
    	set
    -0.06
    学习
    -0.06
    -me
    -0.06
     評
    -0.06
    inars
    -0.06
    死
    -0.06
    ,number
    -0.06
    POSITIVE LOGITS
     Possibly
    0.07
     Blake
    0.07
     Tyson
    0.06
     endIndex
    0.06
    ıldı
    0.06
     जर
    0.06
     maj
    0.06
    ence
    0.06
    [label
    0.06
     INCLUDING
    0.06
    Act Density 0.019%

    No Known Activations