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

    Neuronpedia

    INDEX
    Explanations

    lines of code or comments typically found in programming or scripting texts

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

    non-alphanumeric characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEGGI
    -0.68
     BoxFit
    -0.51
    $}}
    -0.46
    `;
    -0.45
    }`).
    -0.45
    >`;
    -0.45
    findpost
    -0.43
    ''');
    -0.43
    )];
    -0.42
    )}_
    -0.42
    POSITIVE LOGITS
    ////////////////
    1.14
    ################
    0.61
    ////////////
    0.60
    IntoConstraints
    0.56
     nakalista
    0.56
    AndEndTag
    0.54
    //////////////
    0.54
    /////////////
    0.54
     ujednoznacz
    0.52
    ///////////////
    0.52
    Act Density 0.007%

    No Known Activations