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

    Neuronpedia

    INDEX
    Explanations

    statements regarding facts or truths, particularly in the context of evaluations or conclusions

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

    Statements of truth, facts, or myths

    np_acts-logits-general · gemini-2.0-flash

    facts and truth statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reſ
    -0.59
     Houſe
    -0.59
    phazard
    -0.57
     Monfieur
    -0.51
     juſ
    -0.50
     ſche
    -0.50
     ſta
    -0.49
    PhysRevD
    -0.48
     contextes
    -0.47
     houſe
    -0.47
    POSITIVE LOGITS
     facts
    0.61
     fact
    0.60
     truths
    0.57
     Facts
    0.56
    fact
    0.55
    Facts
    0.54
    Fact
    0.53
    richTextPanel
    0.53
    facts
    0.52
     statement
    0.49
    Act Density 0.920%

    No Known Activations