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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cio
    -0.07
     Note
    -0.06
    _c
    -0.06
    _ABC
    -0.06
    -minus
    -0.06
     #=>
    -0.06
     ブ
    -0.06
    Behavior
    -0.06
     lint
    -0.06
     UI
    -0.05
    POSITIVE LOGITS
    ريع
    0.07
     Fransa
    0.07
     اتفاق
    0.06
    ели
    0.06
     ประก
    0.06
    ENARIO
    0.06
     اشاره
    0.06
     wsp
    0.06
     مف
    0.06
    ")}↵
    0.06
    Act Density 0.145%

    No Known Activations