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

    Neuronpedia

    INDEX
    Explanations

    music descriptions

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric expressions—numbers, dates, and quantitative counts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     کیل
    -0.07
     ALTER
    -0.07
     MAS
    -0.06
    )obj
    -0.06
     down
    -0.06
     '_
    -0.06
    _CHECK
    -0.06
     RX
    -0.06
    vide
    -0.06
     magnificent
    -0.06
    POSITIVE LOGITS
     adalah
    0.06
    -rest
    0.06
     появ
    0.06
    	lcd
    0.06
     reprint
    0.06
    ३
    0.06
    едь
    0.06
    <Mesh
    0.06
    ('',
    0.05
    ości
    0.05
    Act Density 0.035%

    No Known Activations