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

    Neuronpedia

    INDEX
    Explanations

    institutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.63
    :///
    -0.62
    ?</
    -0.54
    ">@
    -0.54
    ))=\
    -0.53
    '>{
    -0.52
     Мексичка
    -0.52
    ')));
    -0.50
     =
    -0.49
    `;
    -0.49
    POSITIVE LOGITS
    Rhestr
    0.75
     Majefty
    0.70
     purpoſe
    0.65
     Normdatei
    0.63
     Reſ
    0.60
     فريبيس
    0.60
    #+#
    0.58
     ſtate
    0.58
     Shakspeare
    0.57
     Perſ
    0.57
    Act Density 0.001%

    No Known Activations