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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pery
    -0.07
    Ob
    -0.07
    _RANGE
    -0.07
     trio
    -0.06
     distinction
    -0.06
    privileged
    -0.06
    Limits
    -0.06
    _learn
    -0.06
    Bad
    -0.06
    Convertible
    -0.06
    POSITIVE LOGITS
    .$.
    0.07
     sw
    0.06
     ao
    0.06
     Dare
    0.06
     cửa
    0.06
    '.
    0.06
    ENARIO
    0.06
     {.
    0.06
    |#
    0.06
     puzzles
    0.06
    Act Density 0.003%

    No Known Activations