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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Donald
    -0.07
    بق
    -0.07
    :list
    -0.07
     Trevor
    -0.07
    époque
    -0.06
    pcl
    -0.06
    拂
    -0.06
     neat
    -0.06
    棕色
    -0.06
    direction
    -0.06
    POSITIVE LOGITS
     ||=
    0.07
    öğretim
    0.07
    ────
    0.07
    -heavy
    0.07
     //!<
    0.06
    Jets
    0.06
    Iter
    0.06
    集团
    0.06
     retries
    0.06
     wyłącznie
    0.06
    Act Density 0.000%

    No Known Activations