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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to precision and advanced materials

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

    ultra-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.53
    rhosis
    -0.45
     sumpay
    -0.44
    ucoup
    -0.42
    Soorten
    -0.38
    Décès
    -0.38
     ModelExpression
    -0.38
     considerable
    -0.38
     muualla
    -0.37
     insuffisamment
    -0.37
    POSITIVE LOGITS
     ultra
    0.90
    ultra
    0.79
     Ultra
    0.74
    Ultra
    0.73
    tralight
    0.71
     ULTRA
    0.65
     ультра
    0.64
     ult
    0.60
     super
    0.56
     ultras
    0.52
    Act Density 0.029%

    No Known Activations