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

    Neuronpedia

    INDEX
    Explanations

    constructor

    np_max-act · gemini-2.0-flash

    This neuron activates on the keyword “constructor” (i.e. it detects constructor definitions in code).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Nat
    -0.07
    иту
    -0.07
    ν
    -0.06
     ad
    -0.06
     Каз
    -0.06
    내
    -0.06
    تي
    -0.06
    ξ
    -0.06
    발
    -0.06
     pigs
    -0.06
    POSITIVE LOGITS
    (padding
    0.06
    ück
    0.06
     php
    0.06
    (HttpContext
    0.06
    ρά
    0.06
    .uml
    0.06
    наслід
    0.06
     introduces
    0.06
    싸
    0.06
    ystery
    0.06
    Act Density 0.002%

    No Known Activations