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

    Neuronpedia

    INDEX
    Explanations

    JsonProperty

    np_max-act · gemini-2.0-flash

    The neuron detects code annotations or attributes—most strongly the “[JsonProperty(…) ]” markers that declare JSON‐serializable properties.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ひと
    -0.07
     Pistol
    -0.07
     dict
    -0.06
    Aaron
    -0.06
    "default
    -0.06
    Basic
    -0.06
    世紀
    -0.06
    NewItem
    -0.06
     ApplicationRecord
    -0.06
     getattr
    -0.06
    POSITIVE LOGITS
     );↵
    0.06
     ),↵
    0.06
     fark
    0.06
     yayın
    0.06
     destruct
    0.06
     sher
    0.06
    $h
    0.06
     refl
    0.06
    اعي
    0.06
     equipments
    0.06
    Act Density 0.002%

    No Known Activations