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

    Neuronpedia

    INDEX
    Explanations

    ellipses

    np_max-act · gemini-2.0-flash

    The neuron detects ellipsis‐style continuation markers (sequences of dots like “…”) that signal truncated or “read more/continue reading” text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Keys
    -0.07
     fiat
    -0.06
     manipulating
    -0.06
    pins
    -0.06
     Foot
    -0.06
    恶
    -0.06
    Salt
    -0.06
     inds
    -0.06
    .xaxis
    -0.06
     Arabia
    -0.06
    POSITIVE LOGITS
    \Migrations
    0.06
    @GetMapping
    0.06
     eats
    0.06
    ई
    0.06
    tearDown
    0.06
     сох
    0.06
     pasture
    0.06
    estring
    0.06
    (iOS
    0.06
    (timeout
    0.06
    Act Density 0.024%

    No Known Activations