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

    Neuronpedia

    INDEX
    Explanations

    Place names and proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immediate
    -0.07
     gorge
    -0.07
     ("/
    -0.06
    lazy
    -0.06
    "If
    -0.06
     rat
    -0.06
     Ney
    -0.06
     illumin
    -0.06
    いい
    -0.06
     Ideas
    -0.06
    POSITIVE LOGITS
    곳
    0.09
     REV
    0.08
     علت
    0.07
     ét
    0.07
     Spoj
    0.07
     Đảng
    0.07
    하우
    0.06
    wyn
    0.06
    ευ
    0.06
    اون
    0.06
    Act Density 0.003%

    No Known Activations