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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens that are part of floating-point values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Turkey
    -0.07
     Моск
    -0.06
    uler
    -0.06
     Turkey
    -0.06
    _ANY
    -0.06
     sadly
    -0.06
     stationary
    -0.06
     kf
    -0.06
     Initial
    -0.06
    -issue
    -0.06
    POSITIVE LOGITS
    LETED
    0.07
     ương
    0.06
    _Enable
    0.06
     sequelize
    0.06
    ::::::::::::::
    0.06
    .Navigate
    0.06
    -elements
    0.06
     bazen
    0.06
    funcs
    0.06
    Repository
    0.06
    Act Density 0.114%

    No Known Activations