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

    Neuronpedia

    INDEX
    Explanations

    historical figures and their relationships to political events or dynasties

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

    Preceding Roman numerals or "ibn"

    np_acts-logits-general · gemini-2.0-flash

    names followed by ibn or son

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    modelBuilder
    -0.84
     nakalista
    -0.80
     itſelf
    -0.74
     contextLoads
    -0.69
    Autoritní
    -0.68
    :✨
    -0.68
    Jeografia
    -0.67
     uſed
    -0.66
     houſe
    -0.66
     Majefty
    -0.66
    POSITIVE LOGITS
     II
    0.61
     himself
    0.59
    himself
    0.58
     who
    0.57
    whom
    0.56
     whom
    0.55
     son
    0.55
     figlio
    0.54
     financières
    0.52
    #+#
    0.51
    Act Density 0.242%

    No Known Activations