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

    Neuronpedia

    INDEX
    Explanations

    specific characters and their interactions in narratives

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

    proper names in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.68
    tvguidetime
    -0.57
    twimg
    -0.56
    ]='\
    -0.54
    onOptions
    -0.53
     slick
    -0.53
    XmlAccessorType
    -0.52
     contras
    -0.51
     crocodile
    -0.51
     Torna
    -0.51
    POSITIVE LOGITS
     kræ
    0.43
     humanidade
    0.40
     Ensino
    0.40
     Notwendigkeit
    0.39
     Económica
    0.39
     Wahrheit
    0.38
     ayudado
    0.38
     Glaube
    0.38
     rantai
    0.37
     libremente
    0.37
    Act Density 0.030%

    No Known Activations