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

    Neuronpedia

    INDEX
    Explanations

    echo

    np_max-act · gemini-2.0-flash

    The neuron predominantly activates on floating-point numeric literals (i.e. decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Maryland
    -0.07
     Pag
    -0.07
     taps
    -0.06
    .viewport
    -0.06
    predicted
    -0.06
    .Mark
    -0.06
    .gradient
    -0.06
    .contact
    -0.06
    olin
    -0.06
    spinner
    -0.06
    POSITIVE LOGITS
     أنه
    0.07
    ><![
    0.06
     még
    0.06
     Coch
    0.06
     количе
    0.06
     novo
    0.06
     extrem
    0.06
     파일첨부
    0.06
    'value
    0.06
    _writer
    0.06
    Act Density 0.004%

    No Known Activations