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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and technical specifications

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

    Questions or statements followed by clarifications/corrections

    np_acts-logits-general · gemini-2.0-flash

    discrepancy and clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ideas
    -0.53
     ✭✭
    -0.53
    ocrat
    -0.53
    年来
    -0.50
    hassee
    -0.49
    Portail
    -0.49
     hobbies
    -0.48
    developed
    -0.48
    EnableWeb
    -0.47
     formidable
    -0.47
    POSITIVE LOGITS
     confusing
    0.88
     clarification
    0.88
     unclear
    0.83
     correct
    0.82
     confuses
    0.82
     Confused
    0.80
     incorrect
    0.80
    correct
    0.78
     discrepancy
    0.77
     correto
    0.77
    Act Density 0.537%

    No Known Activations