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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Indianapolis
    -0.07
     cus
    -0.07
     entrepreneurs
    -0.07
    <meta
    -0.07
    凡本网注
    -0.06
    mpl
    -0.06
     Dun
    -0.06
    ottes
    -0.06
    shop
    -0.06
    闫
    -0.06
    POSITIVE LOGITS
    umably
    0.07
    _MACHINE
    0.07
     Emerald
    0.07
     serum
    0.06
    真理
    0.06
    时尚
    0.06
    rift
    0.06
     valuable
    0.06
    涌现出
    0.06
    我能
    0.06
    Act Density 0.011%

    No Known Activations