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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    This neuron detects meta-commentary that calls out or hedges around a vague term—phrases like “the term ‘…’ is …,” “I’d like to point out that …,” or similar clarifications about terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Health
    -0.06
    forces
    -0.06
     počet
    -0.06
     footprint
    -0.06
     Clubs
    -0.06
    young
    -0.06
     attendee
    -0.06
    	default
    -0.06
    -alone
    -0.06
    health
    -0.06
    POSITIVE LOGITS
    loggedin
    0.07
    +'/
    0.06
    +m
    0.06
    IsEmpty
    0.06
     elems
    0.06
    )↵↵↵↵↵
    0.06
    .Txt
    0.06
    _SMS
    0.06
    镇
    0.06
    .ss
    0.06
    Act Density 0.039%

    No Known Activations