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

    Neuronpedia

    INDEX
    Explanations

    cc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     desac
    -0.09
    سلام
    -0.08
    Eh
    -0.08
    ไข
    -0.08
    Minn
    -0.08
    ziehungs
    -0.07
    偷
    -0.07
    Wednesday
    -0.07
    Italian
    -0.07
    agnetic
    -0.07
    POSITIVE LOGITS
     cijfers
    0.09
    _fig
    0.09
     रिपोर्ट
    0.08
     റിപ്പോർ
    0.08
     straw
    0.08
    ожа
    0.07
     Anth
    0.07
     пояс
    0.07
    Outlined
    0.07
     রিপোর্ট
    0.07
    Act Density 0.001%

    No Known Activations