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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺌ
    -0.10
    _FORWARD
    -0.08
     almonds
    -0.07
    .TypeOf
    -0.07
    的就是
    -0.07
    ضة
    -0.07
    áp
    -0.07
     categoryName
    -0.07
    补贴
    -0.07
     Team
    -0.07
    POSITIVE LOGITS
    陵
    0.07
    	fs
    0.07
     sond
    0.07
     _(
    0.07
     Soph
    0.06
    .cont
    0.06
    _dest
    0.06
    ళ
    0.06
    	My
    0.06
    �
    0.06
    Act Density 0.026%

    No Known Activations