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

    Neuronpedia

    INDEX
    Explanations

    <!--

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on floating‐point numeric literals (decimal numbers) embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Size
    -0.07
    ')[
    -0.07
     ">
    -0.07
    ีข
    -0.06
     розрах
    -0.06
    obox
    -0.06
     наруж
    -0.06
     tangent
    -0.06
    .syn
    -0.06
     popup
    -0.06
    POSITIVE LOGITS
    <!--↵
    0.10
     securities
    0.07
    viders
    0.06
    少
    0.06
     //}↵↵
    0.06
    seud
    0.06
    iotics
    0.06
     νεφ
    0.06
    сих
    0.06
     imagined
    0.06
    Act Density 0.000%

    No Known Activations