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

    Neuronpedia

    INDEX
    Explanations

    _match

    np_max-act · gemini-2.0-flash

    This neuron activates on PHP regular‐expression function calls (e.g. preg_match, preg_replace).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     MODIFY
    -0.07
    ávání
    -0.06
     implementations
    -0.06
    OnClick
    -0.06
    ponible
    -0.06
     cardiac
    -0.06
    γορ
    -0.06
    观
    -0.06
     Müş
    -0.06
    .nd
    -0.06
    POSITIVE LOGITS
     امر
    0.07
    ("");
    0.06
    662
    0.06
    Ghost
    0.06
    APPER
    0.06
     BUT
    0.06
    780
    0.06
    ψης
    0.06
    agem
    0.06
    Classic
    0.06
    Act Density 0.003%

    No Known Activations