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

    Neuronpedia

    INDEX
    Explanations

    varied topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contradiction
    -0.06
    ροφορίες
    -0.06
    имости
    -0.06
    否
    -0.06
     рівень
    -0.06
     suggests
    -0.06
    лан
    -0.06
    Раз
    -0.06
     veřej
    -0.06
    Div
    -0.06
    POSITIVE LOGITS
     giy
    0.07
     Camera
    0.06
    395
    0.06
    340
    0.06
    ＼＼
    0.06
    ược
    0.06
     splash
    0.06
    (memory
    0.06
     byli
    0.06
     protested
    0.06
    Act Density 0.000%

    No Known Activations