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

    Neuronpedia

    INDEX
    Explanations

    Scientific measurements over time

    np_max-act · gemini-2.0-flash

    This neuron detects quantitative performance metrics—numerical values (e.g. stability, capacity retention, cycle counts, rates) reported in the material’s performance data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ffset
    -0.07
    .learn
    -0.06
    Friends
    -0.06
    system
    -0.06
     Gow
    -0.06
    .scroll
    -0.06
    ilingual
    -0.06
    заб
    -0.06
    .Game
    -0.06
     antigen
    -0.06
    POSITIVE LOGITS
     rented
    0.07
     ln
    0.07
    SELL
    0.07
     xuyên
    0.06
     '')
    0.06
     hav
    0.06
     sonraki
    0.06
     sme
    0.06
     ores
    0.06
    ชาต
    0.06
    Act Density 0.014%

    No Known Activations