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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Title
    0.40
    나
    0.39
    ˡ
    0.39
    邡
    0.38
     మహ
    0.38
    فة
    0.37
     Unle
    0.37
    ковник
    0.37
    具体的
    0.37
    동
    0.36
    POSITIVE LOGITS
    <h2>
    0.46
     uite
    0.42
    <h5>
    0.41
    iax
    0.40
    StarService
    0.40
    \",\"
    0.40
     moż
    0.39
     rotate
    0.38
    "><
    0.38
     demarc
    0.38
    Act Density 0.004%

    No Known Activations