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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash

    The neuron activates on PHP variable tokens (the “$…” identifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ạch
    -0.07
     entert
    -0.06
    _partitions
    -0.06
     pol
    -0.06
     observer
    -0.06
     manoe
    -0.06
    恩
    -0.06
    Lie
    -0.06
    typing
    -0.06
    ột
    -0.06
    POSITIVE LOGITS
     (£
    0.07
    uo
    0.06
     згідно
    0.06
    $data
    0.06
     forKey
    0.06
     locals
    0.06
    $msg
    0.06
    /usr
    0.06
    "$
    0.06
    ักงาน
    0.06
    Act Density 0.010%

    No Known Activations