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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一般
    -0.07
     Stanford
    -0.07
    stasy
    -0.06
     القانون
    -0.06
     الدولة
    -0.06
    reeNode
    -0.06
    -middle
    -0.06
     詳細
    -0.06
     Luxury
    -0.06
     har
    -0.06
    POSITIVE LOGITS
    ,event
    0.06
     Macro
    0.06
     follower
    0.06
     nilai
    0.06
     आश
    0.06
    azz
    0.06
     Fol
    0.06
     puls
    0.06
    -solid
    0.06
    _perc
    0.05
    Act Density 0.087%

    No Known Activations