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

    Neuronpedia

    INDEX
    Explanations

    speed

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric tokens representing measurements with decimal points (i.e., fractional values in specifications).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    İŞ
    -0.06
    lava
    -0.06
    ubu
    -0.05
     अब
    -0.05
     MCU
    -0.05
    部门
    -0.05
     ю
    -0.05
    _Password
    -0.05
     роль
    -0.05
     Vě
    -0.05
    POSITIVE LOGITS
    .setMax
    0.07
    ClearColor
    0.07
    phalt
    0.07
     sklearn
    0.07
     yii
    0.06
    +N
    0.06
    rego
    0.06
    植物
    0.06
    .Is
    0.06
    ublic
    0.06
    Act Density 0.011%

    No Known Activations