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

    Neuronpedia

    INDEX
    Explanations

    two known values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ləşdirilib
    0.62
    USION
    0.59
    つつ
    0.58
    ONSE
    0.58
     ವಿವಿಧ
    0.57
    种种
    0.57
     వివిధ
    0.57
    тари
    0.56
    +\|\
    0.56
    जीलैंड
    0.55
    POSITIVE LOGITS
     But
    0.65
     двух
    0.64
    Two
    0.62
     данного
    0.61
     Now
    0.61
    But
    0.61
     deux
    0.60
     In
    0.59
     два
    0.58
    に関しては
    0.58
    Act Density 0.001%

    No Known Activations