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

    Neuronpedia

    INDEX
    Explanations

    technical documentation/forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appoint
    -0.08
    حت
    -0.07
    пись
    -0.07
    ноп
    -0.07
    眯
    -0.07
     служ
    -0.06
     signifies
    -0.06
     Greater
    -0.06
     serializers
    -0.06
     Lv
    -0.06
    POSITIVE LOGITS
    (fin
    0.07
    主演
    0.07
    	go
    0.07
     Lear
    0.07
    /reference
    0.06
    gambar
    0.06
    榧
    0.06
    发展机遇
    0.06
    稑
    0.06
    	cur
    0.06
    Act Density 0.078%

    No Known Activations