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

    Neuronpedia

    INDEX
    Explanations

    for + purpose or duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.43
     Nestle
    0.40
    0.38
    િ
    0.38
     Unilever
    0.36
    ون
    0.36
    </td>
    0.35
     Idam
    0.35
     Crab
    0.35
     Chameleon
    0.35
    POSITIVE LOGITS
    ка
    0.49
    .
    0.46
    I
    0.43
    ۔
    0.41
    لس
    0.40
    는
    0.40
    D
    0.38
    го
    0.38
    카
    0.38
    κα
    0.36
    Act Density 0.313%

    No Known Activations