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

    Neuronpedia

    INDEX
    Explanations

    Studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MG
    -0.07
    );↵↵↵
    -0.07
    MING
    -0.07
    いらっしゃ
    -0.07
     mM
    -0.07
     כאמור
    -0.07
    ʯ
    -0.07
     {↵↵
    -0.07
    Rio
    -0.07
     جاء
    -0.07
    POSITIVE LOGITS
     Fn
    0.08
    dict
    0.08
    layout
    0.08
    .Run
    0.07
    ്
    0.07
    奋
    0.07
    友情链接
    0.07
    วง
    0.07
     marc
    0.07
    output
    0.07
    Act Density 0.047%

    No Known Activations