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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash

    The neuron activates on the decimal numeric probability values (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    avi
    -0.07
    Odd
    -0.07
    iasm
    -0.07
    zo
    -0.06
     davidjl
    -0.06
    обав
    -0.06
     Sanford
    -0.06
    AIN
    -0.06
    цями
    -0.06
    зд
    -0.06
    POSITIVE LOGITS
    _DAYS
    0.07
     INDEX
    0.07
    ffff
    0.06
    WebSocket
    0.06
    _self
    0.06
     predecess
    0.06
    (commit
    0.06
     Inside
    0.06
     перест
    0.06
    “我
    0.06
    Act Density 0.001%

    No Known Activations