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

    Neuronpedia

    INDEX
    Explanations

    multi-script text processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sigmoid
    0.46
    班
    0.45
     h
    0.42
    jian
    0.41
     scissor
    0.40
     asem
    0.40
     scambio
    0.40
    済み
    0.40
     treadmill
    0.40
     I
    0.39
    POSITIVE LOGITS
    ני
    0.47
    এ
    0.45
     плюс
    0.44
    Су
    0.44
    सी
    0.44
    Innen
    0.43
    кою
    0.43
    كَ
    0.42
    atifs
    0.42
    вання
    0.41
    Act Density 0.000%

    No Known Activations