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

    Neuronpedia

    INDEX
    Explanations

    terms related to politics and societal issues

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

    preceding nouns or adjectives

    np_acts-logits-general · gemini-2.0-flash

    person types and professional roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     véritables
    -0.53
     própria
    -0.49
     semplicemente
    -0.49
     propres
    -0.49
     cielos
    -0.48
     siguran
    -0.48
     verdaderas
    -0.47
     egne
    -0.47
     allmän
    -0.46
     pattes
    -0.46
    POSITIVE LOGITS
     persons
    1.17
     person
    1.06
     individuals
    0.94
     autorytatywna
    0.94
    persons
    0.93
     فريبيس
    0.90
     professionals
    0.86
    ReusableCell
    0.83
     people
    0.83
     young
    0.82
    Act Density 1.100%

    No Known Activations