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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ola
    -0.08
     #[
    -0.07
     trou
    -0.07
    '])){
↵
    -0.07
     např
    -0.06
     defaultValue
    -0.06
     osp
    -0.06
     Be
    -0.06
    _STAR
    -0.06
    "go
    -0.06
    POSITIVE LOGITS
    담
    0.06
    NEG
    0.06
    sexual
    0.06
     BinaryTree
    0.06
    agina
    0.06
    inals
    0.06
    ọng
    0.06
    ática
    0.06
    /big
    0.06
     Winter
    0.06
    Act Density 0.008%

    No Known Activations