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

    Neuronpedia

    INDEX
    Explanations

    ($

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orbital
    -0.07
     Baby
    -0.07
    Automatic
    -0.07
     Giovanni
    -0.07
    .encoding
    -0.07
     stomach
    -0.07
     الأح
    -0.06
    cuda
    -0.06
     determine
    -0.06
    仮
    -0.06
    POSITIVE LOGITS
    ¸
    0.07
    털
    0.07
     laptops
    0.06
    ΗΣ
    0.06
    mmm
    0.06
    aign
    0.06
    leccion
    0.06
     Taiwan
    0.06
    국
    0.06
     sexism
    0.06
    Act Density 0.013%

    No Known Activations