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

    Neuronpedia

    INDEX
    Explanations

    Home run / slam dunk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doubted
    -0.07
     isEqualToString
    -0.07
     خشک
    -0.07
     dělat
    -0.07
     être
    -0.07
     thái
    -0.07
    ikt
    -0.06
            ↵
    -0.06
    xt
    -0.06
             ↵
    -0.06
    POSITIVE LOGITS
     garnered
    0.07
    Depart
    0.06
    Summon
    0.06
    \Bundle
    0.06
    Feat
    0.06
     contested
    0.06
    -ли
    0.06
     dm
    0.06
    .parsers
    0.06
     슈
    0.06
    Act Density 0.065%

    No Known Activations