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

    Neuronpedia

    INDEX
    Explanations

    Dependence/Responsibility words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Filed
    -0.27
    åıĪ被
    -0.26
    ";}↵
    -0.25
    åIJĪæ³ķ
    -0.25
    -La
    -0.24
    äºĶ
    -0.24
    nit
    -0.24
     cum
    -0.24
    Tick
    -0.24
    uffle
    -0.24
    POSITIVE LOGITS
    èĪ·
    0.29
    ä¸ĩ个
    0.28
    ä¸į管
    0.28
    缴æİ¥
    0.27
    alogy
    0.27
    бо
    0.26
    gments
    0.25
    енд
    0.25
     directly
    0.25
    ilon
    0.24
    Act Density 0.830%

    No Known Activations