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

    Neuronpedia

    INDEX
    Explanations

    character names and their relationships within narratives

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

    names followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Old
    -0.28
     dip
    -0.28
    ↵↵
    -0.28
     zuges
    -0.28
     deveria
    -0.27
     atrás
    -0.26
     ole
    -0.26
     cât
    -0.26
     mater
    -0.26
     old
    -0.25
    POSITIVE LOGITS
    parsedMessage
    0.79
     مشين
    0.76
     AssemblyTitle
    0.76
     GenerationType
    0.71
    ItemBackground
    0.64
    tagHelperRunner
    0.63
    SourceChecksum
    0.63
     queſta
    0.60
     InputDecoration
    0.60
    comuna
    0.60
    Act Density 0.161%

    No Known Activations