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

    Neuronpedia

    INDEX
    Explanations

    critiques related to social intelligence or common sense reasoning

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

    intelligence or ability

    np_acts-logits-general · gemini-2.0-flash

    intelligence and intellect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multer
    -0.51
    Pautan
    -0.50
    icose
    -0.49
    Présentation
    -0.49
    ########.
    -0.49
    Rohy
    -0.48
    likace
    -0.46
     Herv
    -0.46
    Geplaatst
    -0.46
    Наводи
    -0.44
    POSITIVE LOGITS
     intelligence
    1.94
     intellect
    1.78
     intelligent
    1.67
     smart
    1.57
     Intelligence
    1.57
    intelligence
    1.57
     smarter
    1.54
     IQ
    1.51
     brains
    1.50
     smartest
    1.50
    Act Density 0.358%

    No Known Activations