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

    Neuronpedia

    INDEX
    Explanations

    classroom, classes, II

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :\n\n\n\n
    -0.12
    (){}\n
    -0.10
    __':\n
    -0.10
    ...\n\n\n
    -0.10
    âĢ¦.\n\n
    -0.10
    __":\n
    -0.10
    :\n\n\n
    -0.09
    `}\n
    -0.09
    ...\n\n\n\n
    -0.09
    ?\n\n\n\n
    -0.09
    POSITIVE LOGITS
     {}\n\n
    0.14
    __()\n\n
    0.14
    >\n\n
    0.14
    {}\n\n
    0.14
    ')\n\n
    0.14
    ([]);\n\n
    0.14
     '');\n\n
    0.13
    ")\n\n
    0.13
    ';\n\n
    0.13
    ');\n\n
    0.13
    Act Density 0.116%

    No Known Activations