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

    Neuronpedia

    INDEX
    Explanations

    attendance expectations

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurements—especially decimal or fractional values (e.g., attendance rates, percentages, or other metrics) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ping
    -0.08
     impoverished
    -0.07
    脂
    -0.06
    caps
    -0.06
     brigade
    -0.06
    hurst
    -0.06
    _ver
    -0.06
    .throw
    -0.06
     至
    -0.06
     assured
    -0.06
    POSITIVE LOGITS
     autogenerated
    0.07
    �
    0.07
    _NEW
    0.06
    ([
↵
    0.06
     semiclass
    0.06
    )))↵
    0.06
    ))))↵
    0.06
    	Size
    0.06
    ]))
↵
    0.06
     protein
    0.06
    Act Density 0.045%

    No Known Activations