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

    Neuronpedia

    INDEX
    Explanations

    w

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ारक
    -0.07
    杂
    -0.07
     midnight
    -0.06
     Antar
    -0.06
     indiscrim
    -0.06
     dataframe
    -0.06
     programa
    -0.06
     stret
    -0.06
    imiz
    -0.06
    cljs
    -0.06
    POSITIVE LOGITS
    awl
    0.07
    indsay
    0.06
     дея
    0.06
     Packs
    0.06
    _ATTACHMENT
    0.06
     факти
    0.06
     elong
    0.06
     sexes
    0.06
     kvinner
    0.06
     بور
    0.06
    Act Density 0.001%

    No Known Activations