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

    Neuronpedia

    INDEX
    Explanations

    code-related comments and documentation strings

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

    Code snippets with symbols ($)

    np_acts-logits-general · gemini-2.0-flash

    upfield

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ='"+
    -0.47
    databinding
    -0.47
     rapides
    -0.47
    ="'+
    -0.46
    لاعات
    -0.46
    cioni
    -0.45
     bağlantılar
    -0.45
    درسة
    -0.45
    اديم
    -0.45
     fondament
    -0.44
    POSITIVE LOGITS
     elseif
    0.75
    echo
    0.73
    ($
    0.69
    -$
    0.67
     ($
    0.67
    ][$
    0.63
    ,$
    0.63
    php
    0.61
     $
    0.61
    ++$
    0.61
    Act Density 0.025%

    No Known Activations