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

    Neuronpedia

    INDEX
    Explanations

    structured legal or medical language

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

    legal citations and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.60
     pegatina
    -0.55
     idéia
    -0.54
     novio
    -0.50
     Obrador
    -0.49
     novia
    -0.47
    expandindo
    -0.47
     sonrisa
    -0.46
    Tikang
    -0.46
    OGND
    -0.46
    POSITIVE LOGITS
     kasarigan
    0.57
     matrices
    0.40
     Matrices
    0.39
    合
    0.38
    vetrain
    0.38
     contextLoads
    0.38
     cale
    0.36
     apla
    0.36
     UPC
    0.36
     atte
    0.36
    Act Density 0.582%

    No Known Activations