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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of a specific individual, likely related to discussions of their arguments or findings

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

    Vietnamese/Chinese degree symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    answer
    -0.49
    patrón
    -0.44
     valoración
    -0.42
     esquina
    -0.41
     enfans
    -0.41
     reflexión
    -0.41
     cartera
    -0.40
    entire
    -0.40
     answer
    -0.40
    wnętr
    -0.40
    POSITIVE LOGITS
     độ
    2.75
     Độ
    1.70
    Độ
    1.54
    ộ
    1.02
    度
    0.92
     度
    0.80
     đô
    0.78
     degree
    0.75
    度的
    0.71
     Degree
    0.71
    Act Density 0.002%

    No Known Activations