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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    camp
    -0.07
    Count
    -0.07
     effectively
    -0.06
    _SOFT
    -0.06
    ホテル
    -0.06
     dbHelper
    -0.06
    .setHorizontalAlignment
    -0.06
     Milano
    -0.06
    .JComboBox
    -0.06
    living
    -0.06
    POSITIVE LOGITS
     standout
    0.10
     destac
    0.09
    JA
    0.07
    누
    0.07
     выдел
    0.07
     neu
    0.07
     dur
    0.07
    READING
    0.07
     outstanding
    0.07
     ayrı
    0.07
    Act Density 0.013%

    No Known Activations