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

    Neuronpedia

    INDEX
    Explanations

    Device

    np_max-act · gemini-2.0-flash

    This neuron fires on the word “device” (and related patent-style phrasing around invention descriptions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Precio
    -0.07
    RowAtIndexPath
    -0.06
    ORIZATION
    -0.06
    Appointment
    -0.06
     Personen
    -0.06
    -from
    -0.06
    zeigt
    -0.06
    wd
    -0.06
    altet
    -0.06
    _extended
    -0.06
    POSITIVE LOGITS
     Institute
    0.06
    deposit
    0.06
    exampleInputEmail
    0.06
     Magical
    0.06
    λογή
    0.06
     TOM
    0.06
    şam
    0.06
     snatch
    0.06
     Seb
    0.06
    BEGIN
    0.06
    Act Density 0.039%

    No Known Activations