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

    Neuronpedia

    INDEX
    Explanations

    sub:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    0.84
    essentially
    0.82
     (“
    0.72
    )—
    0.71
    <u>
    0.71
    くれる
    0.70
     essentially
    0.70
     “‘
    0.69
    literally
    0.67
     می‌کنند
    0.67
    POSITIVE LOGITS
    :",
    1.84
     {}",
    1.79
    !",
    1.70
    !");
    1.68
    :");
    1.63
    :\
    1.62
    ");
    1.60
    !")
    1.58
     {}".
    1.57
    !\
    1.55
    Act Density 1.558%

    No Known Activations