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

    Neuronpedia

    INDEX
    Explanations

    contrasting viewpoints

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to past‐tense action words that drive the narrative (e.g. “laughed,” “begging,” “captives”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ourage
    -0.07
    isode
    -0.07
     dispositivo
    -0.07
    (inertia
    -0.06
     photographer
    -0.06
    olume
    -0.06
    -mediated
    -0.06
    _to
    -0.06
    adult
    -0.06
    ivan
    -0.06
    POSITIVE LOGITS
     skb
    0.07
     xlink
    0.07
    ıldı
    0.07
     вт
    0.07
     NDP
    0.06
     ₹
    0.06
     воздейств
    0.06
     prank
    0.06
    cntl
    0.06
    (+
    0.06
    Act Density 0.019%

    No Known Activations