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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IT
    -0.08
    Nuitka
    -0.07
    it
    -0.07
     une
    -0.07
    ite
    -0.06
    assigned
    -0.06
    uhl
    -0.06
    提
    -0.06
    扫
    -0.06
     petit
    -0.06
    POSITIVE LOGITS
    steder
    0.07
     hội
    0.07
    doors
    0.07
    .ecore
    0.07
    ックス
    0.06
    :^(
    0.06
     للإ
    0.06
    αιν
    0.06
     partnership
    0.06
     pz
    0.06
    Act Density 0.044%

    No Known Activations