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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on numeric tokens (especially floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .levels
    -0.06
    @GeneratedValue
    -0.06
     DataAccess
    -0.06
    issement
    -0.06
    increments
    -0.06
     пацієн
    -0.06
    체
    -0.06
    <Contact
    -0.06
    .Xtra
    -0.06
     pdu
    -0.06
    POSITIVE LOGITS
    Make
    0.07
    Game
    0.06
     buyer
    0.06
     auto
    0.06
    VG
    0.06
    ValidationError
    0.06
    abinet
    0.06
    available
    0.06
    ermo
    0.06
    eld
    0.06
    Act Density 0.006%

    No Known Activations