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

    Neuronpedia

    INDEX
    Explanations

    the word "the" when it appears near locations like "nation" or "United States"

    oai_token-act-pair · gemini-2.0-flash

    pronouns and common nouns

    np_token-act-pair-logits · gpt-4o-mini

    say "United"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.79
    DoubleQuotes
    -0.75
     ་་
    -0.73
     ―――――
    -0.65
     raiſ
    -0.63
     Daß
    -0.63
     ſte
    -0.62
     ſmall
    -0.61
     houſe
    -0.61
     Theſe
    -0.61
    POSITIVE LOGITS
    MemoryWarning
    0.73
    ulados
    0.54
     her
    0.53
     Trump
    0.51
     his
    0.50
     saw
    0.50
     malha
    0.49
     zum
    0.49
     Thousand
    0.49
    rungsseite
    0.48
    Act Density 1.919%

    No Known Activations