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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "This"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    2.72
    ↵↵↵↵
    1.88
    ↵↵↵
    1.81
     Because
    1.55
    ↵↵↵↵↵
    1.51
     Although
    1.50
     Despite
    1.46
     Throughout
    1.45
    ↵↵↵↵↵↵↵↵
    1.40
     Undoubtedly
    1.38
    POSITIVE LOGITS
     ẞ
    1.28
    ...");
    1.00
    .`);
    0.97
    ẞ
    0.94
    !");
    0.93
    $.}
    0.90
    !";
    0.88
    ;');
    0.88
     \"
    0.88
     阅读全文
    0.87
    Act Density 0.900%

    No Known Activations