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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the JavaScript/TypeScript “this” keyword referencing an object’s own properties or methods.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     deport
    -0.06
     Gand
    -0.06
    qd
    -0.06
     dn
    -0.06
     Bang
    -0.06
     нед
    -0.06
     oud
    -0.06
     Cod
    -0.06
    wan
    -0.06
     Raq
    -0.06
    POSITIVE LOGITS
     The
    0.11
     I
    0.11
    the
    0.10
    this
    0.09
    (this
    0.09
     you
    0.09
    +self
    0.09
     the
    0.09
    =self
    0.09
     we
    0.09
    Act Density 0.038%

    No Known Activations