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

    Neuronpedia

    INDEX
    Explanations

    lot of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endroit
    0.40
    ᒧ
    0.39
     Branches
    0.38
     coincidence
    0.38
     merhabalar
    0.38
     Progress
    0.37
    תר
    0.37
    での
    0.37
     noção
    0.36
    ผู้
    0.36
    POSITIVE LOGITS
     času
    0.78
     времени
    0.73
     시간을
    0.73
     وقت
    0.71
     часу
    0.70
    時間を
    0.69
     czasu
    0.68
    시간
    0.66
     afternoons
    0.65
     χρόνο
    0.64
    Act Density 0.008%

    No Known Activations