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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash

    This neuron picks out the numeric token “4” (especially in the context of “4.0” or section numbering, as in “Industry 4.0”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    nim
    -0.06
    rine
    -0.06
    paint
    -0.06
    _walk
    -0.06
    増
    -0.06
     Stap
    -0.06
    _ten
    -0.06
    _des
    -0.06
     Swim
    -0.06
    tip
    -0.05
    POSITIVE LOGITS
    είται
    0.07
     руковод
    0.07
     availability
    0.07
     rejuven
    0.07
    政治
    0.07
    方法
    0.06
    uck
    0.06
     inverted
    0.06
     variables
    0.06
    保护
    0.06
    Act Density 0.002%

    No Known Activations