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

    Neuronpedia

    INDEX
    Explanations

    code snippets and syntax elements

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

    Code snippets with backticks/brackets

    np_acts-logits-general · gemini-2.0-flash

    archaic and uncommon words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ';
    -0.78
    </strong>
    -0.64
     he
    -0.64
    `;
    -0.63
     «
    -0.62
    ');
    -0.62
    ";
    -0.61
     Am
    -0.59
    ;
    -0.58
     of
    -0.58
    POSITIVE LOGITS
    ſelf
    1.12
    ſelves
    1.07
     myſelf
    0.96
     Monfieur
    0.96
     ſever
    0.95
     uſed
    0.95
     $_(
    0.95
     snippetHide
    0.94
     tartalomajánló
    0.93
     velours
    0.93
    Act Density 0.256%

    No Known Activations