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

    Neuronpedia

    INDEX
    Explanations

    Software licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verr
    -0.07
     involves
    -0.07
     Square
    -0.07
    nan
    -0.07
     Luxury
    -0.07
     built
    -0.07
    avin
    -0.07
     abdom
    -0.07
    墡
    -0.07
    Picture
    -0.07
    POSITIVE LOGITS
    畜牧业
    0.07
    𝓈
    0.06
    .poll
    0.06
    .urls
    0.06
    публи
    0.06
    tensorflow
    0.06
    _MEM
    0.06
    解放军
    0.06
    팩
    0.06
    LLL
    0.06
    Act Density 0.012%

    No Known Activations