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

    Neuronpedia

    INDEX
    Explanations

    the word "fact" and related words that express that something is real

    oai_token-act-pair · gemini-2.0-flash

    fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fact
    -2.27
    fact
    -1.84
     Fact
    -1.64
    Fact
    -1.63
     Tatsache
    -1.45
     FACT
    -1.27
     Facts
    -1.09
     fakta
    -1.09
     hecho
    -1.07
     факт
    -1.05
    POSITIVE LOGITS
    PhysRevLett
    0.67
    muñ
    0.57
     Sinon
    0.55
     getRule
    0.54
    Hentet
    0.53
    zzar
    0.52
     bologna
    0.52
    CreateIndex
    0.52
    uties
    0.51
    dress
    0.50
    Act Density 1.785%

    No Known Activations