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

    Neuronpedia

    INDEX
    Explanations

    product reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crop
    -0.07
     dean
    -0.07
     Kaiser
    -0.07
    に行って
    -0.07
    ("^
    -0.07
    第三个
    -0.06
    (&_
    -0.06
     GLuint
    -0.06
    *angstrom
    -0.06
    宫颈
    -0.06
    POSITIVE LOGITS
    摆
    0.08
     counted
    0.07
    办公
    0.07
    袖
    0.07
    擺
    0.07
    iscrim
    0.07
    lasses
    0.07
    cludes
    0.07
     DOCUMENT
    0.07
    мел
    0.06
    Act Density 0.055%

    No Known Activations