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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any tokens—it isn’t detecting any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    azo
    -0.07
    302
    -0.07
    31
    -0.06
    ROLLER
    -0.06
    28
    -0.06
    -building
    -0.06
     improper
    -0.06
    25
    -0.06
    travel
    -0.06
    29
    -0.06
    POSITIVE LOGITS
    馆
    0.06
    [--
    0.06
    filtro
    0.06
    户
    0.06
    ////↵
    0.06
    wcs
    0.06
     Creed
    0.06
    야
    0.06
     Capcom
    0.06
    .sat
    0.06
    Act Density 0.016%

    No Known Activations