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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash

    The neuron activates on PHP string literals used as keys in associative array definitions (e.g. 'type', 'label', 'name').

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pell
    -0.07
     forte
    -0.06
    vida
    -0.06
     toItem
    -0.06
    PLL
    -0.06
    ohl
    -0.06
     Basement
    -0.06
    eting
    -0.06
    	lcd
    -0.06
    _pan
    -0.06
    POSITIVE LOGITS
     Υπο
    0.07
     Everywhere
    0.07
     qw
    0.06
    Comp
    0.06
     wonderful
    0.06
    -й
    0.06
     Swipe
    0.06
     AR
    0.06
     شار
    0.06
    etrize
    0.06
    Act Density 0.010%

    No Known Activations