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

    Neuronpedia

    INDEX
    Explanations

    terms related to processes and actions in a specific context

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

    try again, make, lethal dose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.54
     Airports
    -0.52
     étrangère
    -0.51
     ainfi
    -0.50
     Wallflower
    -0.49
    potranspiration
    -0.49
     FEEDBACK
    -0.49
    Vraag
    -0.49
     Photographie
    -0.48
    Interactions
    -0.48
    POSITIVE LOGITS
    制
    2.52
     制
    1.82
    製
    1.59
    制的
    1.55
     chế
    1.07
     製
    0.99
    제
    0.95
    制作
    0.82
     제
    0.80
     制作
    0.71
    Act Density 0.002%

    No Known Activations