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

    Neuronpedia

    INDEX
    Explanations

    let's start or talk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    know
    0.48
    𒈠
    0.45
     জানিয়েছে
    0.43
     sapere
    0.43
    ízo
    0.39
    }>
    0.38
    Know
    0.38
    我知道
    0.38
    知道
    0.38
    說是
    0.38
    POSITIVE LOGITS
     lets
    0.62
     Давайте
    0.61
    ’
    0.59
     vamos
    0.56
     давайте
    0.54
    '
    0.54
     Vamos
    0.52
     dive
    0.51
    Vamos
    0.51
     Lets
    0.48
    Act Density 0.034%

    No Known Activations