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

    Neuronpedia

    INDEX
    Explanations

    numeric or code-like patterns and structures

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

    C++ code snippets

    np_acts-logits-general · gemini-2.0-flash

    code blocks and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -1.04
    NameInMap
    -0.98
    expandindo
    -0.96
     للمعارف
    -0.92
    afficheront
    -0.88
    ']);
    -0.88
    '));
    -0.88
    +#+#
    -0.87
    -0.86
     disambiguazione
    -0.84
    POSITIVE LOGITS
     {
    0.63
    ,
    0.55
        
    0.55
    :
    0.47
            
    0.45
    {
    0.45
     estat
    0.42
    <unused62>
    0.42
    0.42
     type
    0.41
    Act Density 0.015%

    No Known Activations