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

    Neuronpedia

    INDEX
    Explanations

    words related to names and locations

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

    Japanese names or titles

    np_acts-logits-general · gemini-2.0-flash

    Japanese names like Aoyagi, Misawa, Yazawa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -1.28
    ,
    -1.16
     (
    -1.10
    .
    -1.06
     T
    -1.01
    ↵
    -1.00
    -
    -0.98
     F
    -0.97
    ↵↵
    -0.97
     E
    -0.97
    POSITIVE LOGITS
     Efq
    2.40
     myſelf
    2.36
     Monfieur
    2.27
     ainfi
    2.25
     auffi
    2.20
     Theſe
    2.19
     ―――――
    2.17
    rungsseite
    2.13
     Anſ
    2.13
     doubtnut
    2.09
    Act Density 0.049%

    No Known Activations