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

    Neuronpedia

    INDEX
    Explanations

    forecasting future probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आजकल
    0.62
     якобы
    0.58
     요즘
    0.58
     вдруг
    0.56
     nowadays
    0.56
    Nowadays
    0.54
    明明
    0.54
     আজকাল
    0.54
     Nowadays
    0.53
     අන
    0.52
    POSITIVE LOGITS
     probably
    1.27
     probablement
    1.26
     probabilmente
    1.24
    probably
    1.16
     provavelmente
    1.16
     probablemente
    1.13
     likely
    1.09
     Probably
    1.07
    Probably
    1.04
     wahrscheinlich
    1.00
    Act Density 0.014%

    No Known Activations