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
    aised
    -0.07
    回暖
    -0.07
    ponential
    -0.07
    odef
    -0.07
    解
    -0.07
    pace
    -0.07
    店加盟
    -0.06
     fence
    -0.06
    lege
    -0.06
     recently
    -0.06
    POSITIVE LOGITS
     Cary
    0.08
    的事实
    0.08
     Freak
    0.07
     finanzi
    0.07
     Karn
    0.07
     admir
    0.07
    もあり
    0.07
     Admir
    0.06
     imagin
    0.06
     Municipal
    0.06
    Act Density 0.031%

    No Known Activations