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

    Neuronpedia

    INDEX
    Explanations

    elements related to data structures and their attributes within coding contexts

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

    Code or data with special characters

    np_acts-logits-general · gemini-2.0-flash

    code, configuration settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.97
     &___
    -0.97
     Мексичка
    -0.93
    ItemBackground
    -0.91
     Савезне
    -0.90
    ⓧ
    -0.89
    InjectAttribute
    -0.88
     kaarangay
    -0.88
     Infórmanos
    -0.88
    saraba
    -0.87
    POSITIVE LOGITS
    </strong>
    0.64
      
    0.62
    </b>
    0.54
        
    0.51
    ’
    0.50
    …
    0.48
    ten
    0.48
    '
    0.47
            
    0.47
    ي
    0.47
    Act Density 0.486%

    No Known Activations