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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of belonging or relational connections

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

    Follows the word "of"

    np_acts-logits-general · gemini-2.0-flash

    act of abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     illustrazione
    -0.64
     tendenza
    -0.58
     the
    -0.58
     ragioni
    -0.55
     disposent
    -0.54
     pagrind
    -0.54
     presentazione
    -0.52
     testemun
    -0.52
     nacer
    -0.51
     jöv
    -0.51
    POSITIVE LOGITS
    )++;
    0.95
    ########.
    0.95
    Tikang
    0.93
     дописавши
    0.89
    PMailer
    0.89
    ;'>
    0.88
    stateProvider
    0.87
    HasAnnotation
    0.86
    AddTagHelper
    0.86
     GenerationType
    0.85
    Act Density 0.549%

    No Known Activations