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

    Neuronpedia

    INDEX
    Explanations

    Large sample sizes

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens and other number‐related figures, effectively picking out quantitative data like sample sizes and statistics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     principal
    -0.06
     nhỏ
    -0.06
     hã
    -0.06
     Tutorial
    -0.06
    ั้
    -0.06
    -yellow
    -0.06
    \Request
    -0.06
    odelist
    -0.06
    _CAM
    -0.06
    endereco
    -0.06
    POSITIVE LOGITS
    Separated
    0.07
     simul
    0.06
    (hero
    0.06
    (sin
    0.06
     openFileDialog
    0.06
     základ
    0.06
    スマ
    0.06
     четвер
    0.06
    Achie
    0.06
    _va
    0.06
    Act Density 0.031%

    No Known Activations