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

    Neuronpedia

    INDEX
    Explanations

    references to specific countries and regions

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

    countries and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schie
    -0.42
    tisch
    -0.41
    AndEndTag
    -0.40
     Fleisch
    -0.35
     dancing
    -0.34
     Schrö
    -0.34
     vaik
    -0.33
    janja
    -0.33
     Schar
    -0.33
     Mush
    -0.32
    POSITIVE LOGITS
    Personensuche
    0.67
    elemField
    0.64
     faſt
    0.63
    StructEnd
    0.63
    StoryboardSegue
    0.60
     poffible
    0.58
    astéroïdes
    0.57
     desertcart
    0.56
     pleaſure
    0.56
     GenerationType
    0.54
    Act Density 0.001%

    No Known Activations