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

    Neuronpedia

    INDEX
    Explanations

    hour

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    use
    -0.08
     Harbour
    -0.07
     downs
    -0.07
    arness
    -0.07
    USE
    -0.07
     paintings
    -0.06
    순
    -0.06
    리어
    -0.06
     disregard
    -0.06
     darling
    -0.06
    POSITIVE LOGITS
    BuildContext
    0.07
    =\"/
    0.07
    यर
    0.07
     التر
    0.06
    '}↵↵
    0.06
    (elem
    0.06
     restr
    0.06
    _perm
    0.06
     DEST
    0.06
     cls
    0.06
    Act Density 0.012%

    No Known Activations