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

    Neuronpedia

    INDEX
    Explanations

    papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fn
    -0.06
     مهد
    -0.06
    曲
    -0.06
    Isl
    -0.06
    _LINE
    -0.06
    .Registry
    -0.06
    repos
    -0.06
     Ken
    -0.06
    isque
    -0.06
    С
    -0.06
    POSITIVE LOGITS
     unreachable
    0.07
    σμό
    0.07
     visited
    0.07
    ่งชาต
    0.07
     hiss
    0.07
    bou
    0.06
     oranı
    0.06
     maxValue
    0.06
    .strip
    0.06
     sorter
    0.06
    Act Density 0.016%

    No Known Activations