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

    Neuronpedia

    INDEX
    Explanations

    code or symbols

    np_max-act · gemini-2.0-flash

    terms related to nuclear weapons and their characteristics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on numeric tokens—especially floating‐point numbers and decimal values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     typed
    -0.07
    	constructor
    -0.07
     дітей
    -0.07
     PV
    -0.06
     如果
    -0.06
     abs
    -0.06
    lahoma
    -0.06
     LI
    -0.06
     concerts
    -0.06
     xr
    -0.06
    POSITIVE LOGITS
    (lock
    0.07
    iture
    0.07
    άβ
    0.06
    놓
    0.06
    フレ
    0.06
    -night
    0.06
    Vote
    0.06
     ellipt
    0.06
     verir
    0.06
    월까지
    0.06
    Act Density 0.101%

    No Known Activations