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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on the start of PHP method signatures—specifically the opening parenthesis and parameter tokens in class function declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    appointed
    -0.07
    _DEAD
    -0.06
    ılan
    -0.06
     American
    -0.06
     Gamer
    -0.06
    -commit
    -0.06
    -American
    -0.06
    оты
    -0.06
    akistan
    -0.06
    hores
    -0.06
    POSITIVE LOGITS
    enaire
    0.07
    .omg
    0.06
    (j
    0.06
     register
    0.06
     disastr
    0.06
    enth
    0.06
    _BLE
    0.06
     신입
    0.06
     kla
    0.06
    :string
    0.06
    Act Density 0.025%

    No Known Activations