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

    Neuronpedia

    INDEX
    Explanations

    names, titles, or specific identifiers associated with individuals or organizations

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

    that often appear in headlines

    np_acts-logits-general · gemini-2.0-flash

    people and organizations named

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.87
     étoit
    -0.80
     itſelf
    -0.80
     myſelf
    -0.79
     avoient
    -0.79
     themſelves
    -0.76
     purpoſe
    -0.75
     enfans
    -0.74
     Efq
    -0.74
     ſeveral
    -0.74
    POSITIVE LOGITS
     to
    0.91
     gets
    0.83
    :
    0.77
     takes
    0.75
     vs
    0.74
     seeks
    0.74
     re
    0.72
     Gets
    0.72
     will
    0.72
     announces
    0.71
    Act Density 0.217%

    No Known Activations