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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associations within technical or data-related contexts

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

    numbers and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     directly
    -0.36
     given
    -0.35
     independente
    -0.34
     تضيفلها
    -0.34
     direto
    -0.34
    |
    -0.33
     revealed
    -0.32
     independent
    -0.31
      
    -0.31
     well
    -0.31
    POSITIVE LOGITS
     betweenstory
    0.86
    ⟬
    0.75
     CreateTagHelper
    0.74
     Taktlose
    0.74
    AndEndTag
    0.72
    WriteTagHelper
    0.72
     ویکی‌آمباردا
    0.70
     propOrder
    0.69
    MessageOf
    0.68
    ſammen
    0.68
    Act Density 0.089%

    No Known Activations