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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    webkit
    -0.07
     Nay
    -0.06
    fov
    -0.06
     खर
    -0.06
     Thương
    -0.06
     phúc
    -0.06
     万
    -0.06
     defiant
    -0.06
    _rhs
    -0.06
    >,</
    -0.05
    POSITIVE LOGITS
     повинна
    0.08
    .onViewCreated
    0.07
    .getActivity
    0.07
     لإ
    0.07
     considering
    0.07
     사망
    0.07
     ό
    0.06
     avant
    0.06
     現
    0.06
     constants
    0.06
    Act Density 0.008%

    No Known Activations