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

    Neuronpedia

    INDEX
    Explanations

    clear terminal command

    np_max-act · gemini-2.0-flash

    This neuron activates on code tokens used to clear or reset the console/terminal (e.g. system calls like “clear” or “cls”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     TZ
    -0.07
    _indicator
    -0.07
    ลด
    -0.07
    =event
    -0.07
    Todd
    -0.07
    WARD
    -0.07
    方向
    -0.07
     appro
    -0.06
     до
    -0.06
    ffset
    -0.06
    POSITIVE LOGITS
     programmer
    0.07
    'r
    0.06
     Pistol
    0.06
    Orm
    0.06
     durability
    0.06
    aysia
    0.06
     erad
    0.06
    asticsearch
    0.06
    ToInt
    0.06
    _REPO
    0.06
    Act Density 0.003%

    No Known Activations