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

    Neuronpedia

    INDEX
    Explanations

    choices or sequencing

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing decimal points (floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     spins
    -0.08
     URLRequest
    -0.07
     تل
    -0.06
    _EMAIL
    -0.06
     nữa
    -0.06
     bail
    -0.06
     BEN
    -0.06
     slaughter
    -0.06
     исследования
    -0.06
     salts
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Spy
    0.07
     Malaysian
    0.07
    urb
    0.06
     jedn
    0.06
    กลาง
    0.06
     الجديد
    0.06
    Monad
    0.06
     lying
    0.06
    -Th
    0.06
    Act Density 0.036%

    No Known Activations