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

    Neuronpedia

    INDEX
    Explanations

    foreign words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    или
    0.46
    ка
    0.46
    те
    0.41
    characteristics
    0.40
    ти
    0.40
    ালে
    0.38
    к
    0.37
    的
    0.37
    selective
    0.37
    properties
    0.36
    POSITIVE LOGITS
     tarafından
    0.47
     oleh
    0.44
     från
    0.43
     nejen
    0.41
     został
    0.40
     Şimdi
    0.38
     Ancak
    0.38
     그룹
    0.38
     Pentru
    0.37
    졌다
    0.37
    Act Density 0.002%

    No Known Activations