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

    Neuronpedia

    INDEX
    Explanations

    punctuation, stop words

    np_max-act · gemini-2.0-flash

    The neuron primarily detects floating-point numeric tokens (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     glaciers
    -0.06
    軍
    -0.06
     Halloween
    -0.06
    _py
    -0.06
    oky
    -0.06
     foam
    -0.06
     nhưng
    -0.06
     Hydro
    -0.06
     bitcoins
    -0.06
     getLogger
    -0.06
    POSITIVE LOGITS
     İç
    0.07
     відмов
    0.07
    Workflow
    0.06
    ριος
    0.06
    reece
    0.06
     immense
    0.06
    portfolio
    0.06
    ्यक
    0.06
    xDD
    0.06
     bordel
    0.06
    Act Density 0.109%

    No Known Activations