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

    Neuronpedia

    INDEX
    Explanations

    text at the end of paragraphs with a conversational tone

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovic
    -0.07
    åħ¶ä¸Ń
    -0.06
     Statue
    -0.06
    coming
    -0.06
    edback
    -0.06
    ãĥ¼ãĥķ
    -0.06
    onga
    -0.06
    stat
    -0.06
    ↵   ↵
    -0.06
    kommen
    -0.05
    POSITIVE LOGITS
    Lastly
    0.14
     finally
    0.13
     Lastly
    0.13
    Finally
    0.11
     Finally
    0.10
    æľĢåIJİ
    0.10
     ultimately
    0.10
     overall
    0.10
     bottom
    0.10
     final
    0.09
    Act Density 0.027%

    No Known Activations