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

    Neuronpedia

    INDEX
    Explanations

    Studies and trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whore
    -0.07
     Alma
    -0.06
     administrations
    -0.06
     INA
    -0.06
    优秀
    -0.06
     Hentai
    -0.06
     orb
    -0.06
     Guil
    -0.06
     Ur
    -0.06
     Rum
    -0.06
    POSITIVE LOGITS
     fieldType
    0.07
     остан
    0.07
    "label
    0.06
    	an
    0.06
    chr
    0.06
     другими
    0.06
    ="../
    0.06
    無しさん
    0.06
     pouco
    0.06
    ,readonly
    0.06
    Act Density 0.055%

    No Known Activations