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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Telegram
    -0.07
     diagram
    -0.07
     compuls
    -0.06
    쌨
    -0.06
     apprent
    -0.06
    Industrial
    -0.06
    멂
    -0.06
    就像是
    -0.06
    壸
    -0.06
    .dispose
    -0.06
    POSITIVE LOGITS
    מרכ
    0.08
     Stein
    0.08
    スキ
    0.07
    رن
    0.07
    fony
    0.07
    #
    0.07
     למנוע
    0.07
     stripe
    0.07
     bases
    0.07
     baker
    0.07
    Act Density 0.013%

    No Known Activations