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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (especially decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Courses
    -0.07
     드라마
    -0.06
    تی
    -0.06
    559
    -0.06
     Special
    -0.06
    �
    -0.06
    itě
    -0.06
     Parse
    -0.06
     Canvas
    -0.06
    電視
    -0.06
    POSITIVE LOGITS
     invo
    0.07
    荒
    0.06
    .unlink
    0.06
     nghề
    0.06
    0.06
    梁
    0.06
    .lp
    0.06
    .fetchone
    0.06
     Provincial
    0.06
    331
    0.06
    Act Density 0.048%

    No Known Activations