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

    Neuronpedia

    INDEX
    Explanations

    statements related to election integrity and voter registration

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

    before a quotation mark

    np_acts-logits-general · gemini-2.0-flash

    legal and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poichè
    -0.96
     således
    -0.82
     ainfi
    -0.77
     feroit
    -0.76
     endast
    -0.76
     אך
    -0.75
    几人
    -0.74
     آنان
    -0.73
    깥
    -0.73
     auroit
    -0.72
    POSITIVE LOGITS
     somebody
    1.07
     really
    1.03
     everybody
    1.02
     [
    1.01
     kind
    0.99
     basically
    0.97
     sort
    0.96
     maybe
    0.94
    somebody
    0.93
     anybody
    0.90
    Act Density 1.603%

    No Known Activations