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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash

    This neuron activates most strongly on the substring “sent” (as in “presented”), so it is essentially detecting occurrences of “sent.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     엘
    -0.07
    :]↵
    -0.06
     ее
    -0.06
    [A
    -0.06
     Retreat
    -0.06
    =query
    -0.06
     Bě
    -0.06
     broken
    -0.06
     Data
    -0.06
     thin
    -0.06
    POSITIVE LOGITS
    ?>
    0.07
    _possible
    0.07
    flashdata
    0.06
    十一
    0.06
     pornografia
    0.06
    $lang
    0.06
    .LayoutControlItem
    0.06
    yat
    0.06
    (MediaType
    0.06
     фил
    0.06
    Act Density 0.001%

    No Known Activations