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

    Neuronpedia

    INDEX
    Explanations

    dose levels

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “low-level” or “low-dose” treatments or exposures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    EFAULT
    -0.08
     collect
    -0.07
    _dataset
    -0.07
     Bottle
    -0.07
    استان
    -0.07
     herpes
    -0.07
     번
    -0.06
     Gospel
    -0.06
     unn
    -0.06
    ippines
    -0.06
    POSITIVE LOGITS
     Burg
    0.07
    ！！↵↵
    0.07
    sak
    0.07
    .Scroll
    0.06
    rib
    0.06
    _pb
    0.06
    .dm
    0.06
    "},
    0.06
    imest
    0.06
    _Form
    0.06
    Act Density 0.019%

    No Known Activations