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

    Neuronpedia

    INDEX
    Explanations

    "just that" clarification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     notify
    -0.08
    xz
    -0.07
    相邻
    -0.07
    滧
    -0.07
     treaties
    -0.07
     respects
    -0.07
    祢
    -0.07
    视线
    -0.06
     aggregate
    -0.06
    _excel
    -0.06
    POSITIVE LOGITS
     dai
    0.08
    どんどん
    0.07
    になる
    0.07
    noun
    0.07
     già
    0.07
    なのだ
    0.07
    ريا
    0.07
    才能够
    0.07
    dfa
    0.07
    .Generation
    0.07
    Act Density 0.070%

    No Known Activations