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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash

    This neuron fires primarily on occurrences of the identifier “self” in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Stone
    -0.06
    Harness
    -0.06
     Slots
    -0.06
    conference
    -0.06
    $results
    -0.06
    Authorize
    -0.06
     solid
    -0.06
    IENT
    -0.06
     cuisine
    -0.06
    .bad
    -0.06
    POSITIVE LOGITS
    ;(
    0.08
     इ
    0.07
    ующие
    0.07
     rencontr
    0.07
    ﺪ
    0.06
    ãeste
    0.06
    _NET
    0.06
    ôt
    0.06
     publisher
    0.06
     çıkart
    0.06
    Act Density 0.032%

    No Known Activations