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

    Neuronpedia

    INDEX
    Explanations

    discussions related to specific social or political groups and their dynamics

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

    in academic circles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.41
     ब्रेकडाउन
    -0.39
    出版年
    -0.39
    Становништво
    -0.36
     Tieren
    -0.35
    lossians
    -0.35
     Kriege
    -0.35
    给我们
    -0.34
    ']").
    -0.34
    ]').
    -0.34
    POSITIVE LOGITS
     circles
    1.48
     círculos
    1.23
    circles
    1.16
     Circles
    1.06
    Circles
    0.98
     Kreise
    0.88
     circle
    0.86
     quarters
    0.85
     círculo
    0.83
    circle
    0.78
    Act Density 0.057%

    No Known Activations