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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash

    The neuron selectively detects the semicolon separators used to delimit multiple parties or offices (e.g. in a list of defendants) in a legal-case caption header.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	free
    -0.07
    LAB
    -0.07
     slavery
    -0.07
    !***
    -0.07
    -tw
    -0.07
     microseconds
    -0.06
    cou
    -0.06
     relu
    -0.06
    -actions
    -0.06
    Storyboard
    -0.06
    POSITIVE LOGITS
     стать
    0.06
    ;
    0.06
     sit
    0.06
     firmalar
    0.06
     $(".
    0.06
    estruct
    0.06
     turn
    0.05
    icts
    0.05
     actionPerformed
    0.05
     jars
    0.05
    Act Density 0.006%

    No Known Activations