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

    Neuronpedia

    INDEX
    Explanations

    references to computed values or mathematical expressions

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

    Text after forward slashes

    np_acts-logits-general · gemini-2.0-flash

    paths and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </i>
    -0.77
    '));
    -0.64
    "));
    -0.63
     tanto
    -0.63
    ]);
    -0.60
     enough
    -0.58
    </b>
    -0.57
    ,
    -0.57
     ens
    -0.57
     De
    -0.56
    POSITIVE LOGITS
     $/$
    1.14
     @"/
    1.13
    {}/
    1.13
    ={`/
    1.09
    ../
    1.07
     purpoſe
    1.05
     $/
    1.04
    ('/
    1.01
    +'/
    1.00
    /*
    0.99
    Act Density 0.386%

    No Known Activations