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

    Neuronpedia

    INDEX
    Explanations

    domain extensions followed by slash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cierta
    0.67
     articles
    0.62
     கிறிஸ்துவின்
    0.60
     certain
    0.59
     vya
    0.59
     albeit
    0.58
    رهای
    0.58
     frü
    0.57
    લ
    0.56
    Editorial
    0.56
    POSITIVE LOGITS
    /)
    2.28
    /',
    2.28
    /,
    2.23
    /),
    2.19
    /');
    2.08
    /",
    2.05
    /).
    1.98
    /;
    1.92
    /</
    1.91
    /");
    1.89
    Act Density 0.219%

    No Known Activations