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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting in text

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

    Code snippets or filepaths

    np_acts-logits-general · gemini-2.0-flash

    viruses and computer code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.57
    لينكات
    -0.54
    BagConstraints
    -0.54
    الدراسه
    -0.53
     kaynağından
    -0.51
    LabelTagHelper
    -0.50
    ruik
    -0.50
    classnames
    -0.48
    GOTREF
    -0.48
     GenerationType
    -0.47
    POSITIVE LOGITS
    <eos>
    0.89
    expandindo
    0.87
     виправивши
    0.78
     filepath
    0.74
    دانشنامهٔ
    0.74
    filepath
    0.65
    
    0.64
     pinulongan
    0.62
    Autoritní
    0.62
     Ended
    0.60
    Act Density 0.312%

    No Known Activations