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

    Neuronpedia

    INDEX
    Explanations

    characteristic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    46
    -0.08
     Menu
    -0.07
    430
    -0.07
    442
    -0.07
    877
    -0.07
     userRepository
    -0.07
     Rub
    -0.06
    433
    -0.06
    439
    -0.06
    11
    -0.06
    POSITIVE LOGITS
     characteristics
    0.12
     Characteristics
    0.10
     характеристики
    0.09
     characteristic
    0.08
    emade
    0.08
     Hazard
    0.08
    “
    0.07
     trademark
    0.07
     مشکل
    0.07
    hardt
    0.07
    Act Density 0.018%

    No Known Activations