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

    Neuronpedia

    INDEX
    Explanations

    scattering and loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Foundation
    -0.06
    isc
    -0.06
    enumerate
    -0.06
    วด
    -0.06
    ager
    -0.06
    (Core
    -0.06
    Bearer
    -0.06
     минут
    -0.06
     Hà
    -0.06
     Pur
    -0.06
    POSITIVE LOGITS
     Recommend
    0.07
    tere
    0.07
     정치
    0.07
    ICIENT
    0.06
    talk
    0.06
    kie
    0.06
    ัฐ
    0.06
    LU
    0.06
    _SUPPORT
    0.06
     берем
    0.06
    Act Density 0.030%

    No Known Activations