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

    Neuronpedia

    INDEX
    Explanations

    Arms raised upwards

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of limbs and their positioning or restraint (e.g. “arms lifted above head,” “wrists locked,” “legs stretched out”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ích
    -0.06
    (level
    -0.06
    _packet
    -0.06
    ENU
    -0.06
    'We
    -0.06
    igate
    -0.06
     rumored
    -0.06
    تها
    -0.06
    userService
    -0.06
    _algorithm
    -0.06
    POSITIVE LOGITS
     constexpr
    0.06
    .getInput
    0.06
    ไฟ
    0.06
     вы
    0.06
     Pip
    0.06
    /rc
    0.06
     Weinstein
    0.06
     مشارکت
    0.06
     phosph
    0.06
    Comparison
    0.06
    Act Density 0.010%

    No Known Activations