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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash

    This neuron detects special control/formatting tokens (e.g. header or end‐of‐text markers) rather than natural language words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    idia
    -0.07
    никами
    -0.07
    Mais
    -0.07
     alunos
    -0.07
    (Collision
    -0.07
    UDIO
    -0.07
    (pm
    -0.07
    _below
    -0.06
     shepherd
    -0.06
    (My
    -0.06
    POSITIVE LOGITS
    aspberry
    0.06
    acionales
    0.06
     chrono
    0.06
     Raspberry
    0.06
     оброб
    0.06
     raspberry
    0.06
     pakistan
    0.06
    wrapper
    0.06
    ']!='
    0.06
     المدينة
    0.06
    Act Density 0.071%

    No Known Activations