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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric tokens (years, numbers, and other digit sequences).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .WEST
    -0.07
     entertaining
    -0.07
     birth
    -0.07
    Tam
    -0.07
     Rivers
    -0.07
    _DIV
    -0.07
    <object
    -0.06
    .Download
    -0.06
    Ｙ
    -0.06
    aguay
    -0.06
    POSITIVE LOGITS
    ática
    0.06
    -↵
    0.06
    reset
    0.06
    려요
    0.06
     textbook
    0.06
    index
    0.06
     onCreateOptionsMenu
    0.06
    cream
    0.06
    WindowState
    0.05
    /)↵
    0.05
    Act Density 0.056%

    No Known Activations