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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sis
    -0.08
    CardContent
    -0.07
     bona
    -0.07
    _SMS
    -0.07
     initData
    -0.07
     coord
    -0.07
    uele
    -0.06
     Lös
    -0.06
    .End
    -0.06
     ballo
    -0.06
    POSITIVE LOGITS
     проблеми
    0.06
     forcefully
    0.06
    ่ม
    0.05
     Â
    0.05
    자동
    0.05
    (instance
    0.05
     і
    0.05
     kriz
    0.05
     Thủ
    0.05
     الأمر
    0.05
    Act Density 0.008%

    No Known Activations