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

    Neuronpedia

    INDEX
    Explanations

    syntax-related elements in code, such as punctuation and structural keywords

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

    Code-related syntax (parentheses, brackets, semicolons)

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </strong>
    -0.63
    حياتها
    -0.59
    richTextPanel
    -0.59
     صوتيه
    -0.59
    verwijspagina
    -0.58
    fromnode
    -0.53
    soort
    -0.52
    حياته
    -0.49
    Troll
    -0.49
    :✨
    -0.48
    POSITIVE LOGITS
    principalColumn
    0.74
    ")));
    0.58
    _();
    0.56
    ]<<"
    0.56
     "),
    0.54
     ');
    0.54
    viano
    0.53
    ).\\
    0.53
    fflush
    0.53
    "]];
    0.52
    Act Density 0.086%

    No Known Activations