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

    Neuronpedia

    INDEX
    Explanations

    PM/AM

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (especially decimals, version numbers, timestamps).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     uncomfortable
    -0.07
     한번
    -0.07
    forder
    -0.07
    bonus
    -0.06
    autorelease
    -0.06
    _first
    -0.06
    ILD
    -0.06
     birinci
    -0.06
     stomach
    -0.06
     AD
    -0.06
    POSITIVE LOGITS
     UserService
    0.07
    ='".
    0.06
     sanitary
    0.06
     hij
    0.06
     semiclass
    0.06
     месяца
    0.06
     conformity
    0.06
    =sys
    0.06
    -org
    0.06
    tsx
    0.06
    Act Density 0.002%

    No Known Activations