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

    Neuronpedia

    INDEX
    Explanations

    processes

    np_max-act · gemini-2.0-flash

    The neuron responds to long, multi-syllable technical or formal nouns (often domain-specific terminology) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    usra
    -0.07
    arsed
    -0.06
     Faces
    -0.06
     النو
    -0.06
    haus
    -0.06
    815
    -0.06
     kuvvet
    -0.06
    воля
    -0.06
     někdy
    -0.05
     citiz
    -0.05
    POSITIVE LOGITS
     aumento
    0.09
     consistency
    0.08
    人気
    0.07
     outfits
    0.07
     rotation
    0.07
    <b
    0.07
     شدن
    0.07
     lanç
    0.07
     tipos
    0.07
    _message
    0.07
    Act Density 0.314%

    No Known Activations