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
    _true
    -0.07
    부
    -0.06
    stdarg
    -0.06
    (expected
    -0.06
    _restore
    -0.06
    declar
    -0.06
    (my
    -0.06
    section
    -0.06
    ηρε
    -0.06
    endo
    -0.06
    POSITIVE LOGITS
    Š
    0.06
     ром
    0.06
     آزاد
    0.06
    .scrollTop
    0.06
    ως
    0.06
    .mipmap
    0.06
    .forChild
    0.06
     покол
    0.06
     garg
    0.05
    -abs
    0.05
    Act Density 0.223%

    No Known Activations