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

    Neuronpedia

    INDEX
    Explanations

    state or action

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on occurrences of the verb “run” (including “run,” “running,” etc.), i.e. instruction/execution commands.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    Fr
    -0.06
    _multiplier
    -0.06
    (max
    -0.06
    746
    -0.06
     Dom
    -0.06
    _ring
    -0.06
     Polymer
    -0.06
     Yam
    -0.06
     BLUE
    -0.06
    POSITIVE LOGITS
    ball
    0.06
     Dere
    0.06
     DataBase
    0.06
    _compiler
    0.06
     convened
    0.06
    럭
    0.06
    有的
    0.06
    ');?>"
    0.06
    reetings
    0.06
    ')?></
    0.06
    Act Density 0.108%

    No Known Activations