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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    إل
    -0.07
    دافع
    -0.07
    erta
    -0.07
    ichte
    -0.07
    opers
    -0.07
    ls
    -0.07
    唱
    -0.07
     develop
    -0.07
     payer
    -0.07
     LA
    -0.07
    POSITIVE LOGITS
    鱼
    0.08
    _ENV
    0.07
     muff
    0.07
    本站
    0.07
     mould
    0.07
    .UserService
    0.07
    麻
    0.07
     COD
    0.07
     smoothed
    0.07
    .Sort
    0.06
    Act Density 0.102%

    No Known Activations