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

    Neuronpedia

    INDEX
    Explanations

    poll

    np_max-act · gemini-2.0-flash

    polls and voting-related actions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of voting or polls—i.e. words used to invite or report user votes (e.g. “vote,” “poll,” “voting”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     prompts
    -0.07
     Fak
    -0.07
     dream
    -0.07
     pruning
    -0.06
     �
    -0.06
     ак
    -0.06
    多少
    -0.06
     McC
    -0.06
    ()).
    -0.06
    orc
    -0.06
    POSITIVE LOGITS
    crease
    0.07
    licant
    0.07
     courte
    0.06
    ισμού
    0.06
     Vote
    0.06
     إد
    0.06
     бла
    0.06
     муницип
    0.06
    arine
    0.06
    .hamcrest
    0.06
    Act Density 0.012%

    No Known Activations