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

    Neuronpedia

    INDEX
    Explanations

    difference

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numbers—especially statistics-like values (e.g. “3.05”, “3.08”)—highlighting numeric measurements or test results.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     left
    -0.06
    تها
    -0.06
     wavelengths
    -0.06
     آموزش
    -0.06
    _signal
    -0.06
    刚才
    -0.06
    _classes
    -0.06
    arend
    -0.05
     А
    -0.05
    爾
    -0.05
    POSITIVE LOGITS
    .containsKey
    0.07
    ckså
    0.07
    .Mvc
    0.07
     výsledky
    0.07
     ув
    0.07
    送
    0.07
    _te
    0.07
    getInt
    0.07
    разу
    0.06
    .Drawable
    0.06
    Act Density 0.012%

    No Known Activations