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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     s
    0.54
     Signal
    0.49
     Bulan
    0.48
     Gambar
    0.46
     Pant
    0.44
     Z
    0.44
     Silver
    0.43
     Ret
    0.43
     Rail
    0.42
     Timber
    0.42
    POSITIVE LOGITS
     година
    0.57
    нета
    0.53
     তারিখে
    0.51
    🗓
    0.48
    pm
    0.48
    ippings
    0.47
    वां
    0.47
    ник
    0.46
     रोजी
    0.46
    .
    0.46
    Act Density 0.026%

    No Known Activations