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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people

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

    female names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cessite
    -0.31
    foglal
    -0.31
    leyebilirsiniz
    -0.29
     Ră
    -0.28
     מק
    -0.27
    ække
    -0.27
    æl
    -0.26
    `<
    -0.26
    ാല
    -0.25
     wrong
    -0.25
    POSITIVE LOGITS
     Olga
    1.13
     Sonia
    1.07
     Tanya
    1.04
     Lydia
    1.03
     Wanda
    1.02
     Nadia
    1.01
     Elsa
    1.00
    Olga
    1.00
     Ingrid
    0.98
     Miriam
    0.95
    Act Density 0.006%

    No Known Activations