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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -2.09
    ।
    -1.54
     QtGui
    -1.51
     "
    -1.50
    甚至
    -1.49
    ：……
    -1.49
    。
    -1.49
     }],
    -1.47
     hatta
    -1.46
    haviours
    -1.34
    POSITIVE LOGITS
    .
    1.75
     The
    1.54
    这也是
    1.51
    uyla
    1.51
     Also
    1.42
    違います
    1.41
    Fotografía
    1.41
     Flexib
    1.39
    踔
    1.38
    </strong>
    1.37
    Act Density 0.029%

    No Known Activations