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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens in license headers—especially version and date numbers (e.g. “Version 1.0.0”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    isContained
    -0.07
    sorting
    -0.07
     callers
    -0.07
    請
    -0.06
     جهان
    -0.06
    ้องการ
    -0.06
     вол
    -0.06
    ’à
    -0.06
    	gr
    -0.06
    .RunWith
    -0.06
    POSITIVE LOGITS
     actresses
    0.07
    730
    0.06
    ový
    0.06
    ORIES
    0.06
     exhilar
    0.06
    /target
    0.06
    �
    0.06
    Really
    0.06
    ẫu
    0.06
     дія
    0.06
    Act Density 0.006%

    No Known Activations