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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (tokens representing decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     द
    -0.07
     Thom
    -0.06
     tabIndex
    -0.06
    ，或
    -0.06
    eron
    -0.06
     KM
    -0.06
    ILD
    -0.06
     Woman
    -0.06
     والت
    -0.06
     Studi
    -0.06
    POSITIVE LOGITS
    /mod
    0.06
     apartment
    0.06
    .global
    0.06
    ursive
    0.06
    ”—
    0.06
     teknoloj
    0.06
     catch
    0.06
     oval
    0.06
    ..."↵
    0.06
    ansas
    0.06
    Act Density 0.114%

    No Known Activations