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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by numeric tokens or numerical expressions (e.g., digits, decimal values, and measurement numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Schul
    -0.07
     inflate
    -0.06
     antib
    -0.06
    Prop
    -0.06
     hisset
    -0.06
     Angle
    -0.06
     Reload
    -0.06
     Employ
    -0.06
    elihood
    -0.06
    roph
    -0.05
    POSITIVE LOGITS
    ,!
    0.07
    irts
    0.06
    (::
    0.06
    0.06
     eternity
    0.06
    IGIN
    0.06
    ỹ
    0.06
     searchTerm
    0.06
    .Weight
    0.06
     indefinite
    0.06
    Act Density 0.060%

    No Known Activations