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

    Neuronpedia

    INDEX
    Explanations

    references to fundamental truths and insights

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

    statements of truth or insight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.57
    AndEndTag
    -0.56
    ſelves
    -0.56
     houſe
    -0.52
    SequentialGroup
    -0.51
    ſelf
    -0.51
     Houſe
    -0.49
    ftance
    -0.48
    cretion
    -0.48
     Anſ
    -0.48
    POSITIVE LOGITS
     truths
    0.59
     Truths
    0.52
     verdades
    0.52
     constat
    0.43
     facts
    0.43
     conclusiones
    0.43
     Erwartungen
    0.42
     Aussagen
    0.41
     conclusions
    0.41
    法則
    0.39
    Act Density 0.299%

    No Known Activations