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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act · gemini-2.0-flash

    This neuron detects horizontal separator lines or section breaks made up of repeated punctuation characters (e.g. sequences of “—” or “===”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     yapıyor
    -0.07
     curses
    -0.06
    .getOutputStream
    -0.06
     newer
    -0.06
    ITAL
    -0.06
    .FILE
    -0.06
     страны
    -0.06
    ISED
    -0.06
    ARING
    -0.06
    tığı
    -0.06
    POSITIVE LOGITS
     Backpack
    0.07
    descripcion
    0.06
     dns
    0.06
     Пов
    0.06
     대통령
    0.06
    .LoggerFactory
    0.06
     wł
    0.06
     Ga
    0.06
     facilitate
    0.06
    作为
    0.06
    Act Density 0.004%

    No Known Activations