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

    Neuronpedia

    INDEX
    Explanations

    Plays and academia

    np_max-act · gemini-2.0-flash

    The neuron detects special control or metadata tokens (e.g. start/end header markers and end-of-text markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gratitude
    -0.07
     gratuit
    -0.07
     pyplot
    -0.07
     bundan
    -0.07
     چرخ
    -0.07
    프
    -0.07
     συν
    -0.07
     surreal
    -0.06
     shaft
    -0.06
    _exp
    -0.06
    POSITIVE LOGITS
     مهر
    0.07
     HIS
    0.07
    รอง
    0.06
    ZeroWidthSpace
    0.06
     Α
    0.06
     inset
    0.06
    可
    0.06
    ioned
    0.06
     onset
    0.06
    biased
    0.06
    Act Density 0.009%

    No Known Activations