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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Interr
    -0.06
     المش
    -0.06
    發展
    -0.06
     застос
    -0.06
    з
    -0.06
    adlo
    -0.06
    _Tr
    -0.06
    Geo
    -0.06
     میدان
    -0.06
     Müz
    -0.06
    POSITIVE LOGITS
    -dark
    0.07
    	rd
    0.07
     ($
    0.07
    "↵↵↵
    0.07
     норм
    0.07
    “.
    0.06
    !“↵↵
    0.06
    ={[
    0.06
    -ios
    0.06
    =username
    0.06
    Act Density 0.002%

    No Known Activations