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

    Neuronpedia

    INDEX
    Explanations

    crowded

    np_max-act · gemini-2.0-flash

    The neuron activates on words describing crowd levels or busy/packed conditions (e.g. “packed,” “crowded,” “crowds”). It thus detects mentions of crowdedness or how busy a place or event is.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Steam
    -0.07
     skutečně
    -0.07
    (per
    -0.06
    (interval
    -0.06
     sidelines
    -0.06
     torture
    -0.06
    feld
    -0.06
     Splash
    -0.06
     Karen
    -0.06
     curriculum
    -0.06
    POSITIVE LOGITS
    .Void
    0.06
     nationalists
    0.06
    401
    0.06
    _IM
    0.06
    огра
    0.06
     tenía
    0.06
    ???
    0.06
     Difficulty
    0.06
     Sas
    0.06
     inj
    0.06
    Act Density 0.019%

    No Known Activations