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

    Neuronpedia

    INDEX
    Explanations

    geographical identifiers and place names

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

    Russian suffixes and Iberian Peninsula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.33
    volume
    -0.33
     tanam
    -0.30
    Hons
    -0.29
    Hutch
    -0.29
    Finn
    -0.29
    event
    -0.29
     volatility
    -0.28
    Deel
    -0.28
    rtner
    -0.28
    POSITIVE LOGITS
    ской
    1.09
    ская
    1.03
    ских
    1.00
    ского
    0.98
    скую
    0.97
    ские
    0.96
    скими
    0.94
    ский
    0.93
    ської
    0.92
    ским
    0.89
    Act Density 0.001%

    No Known Activations