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

    Neuronpedia

    INDEX
    Explanations

    bounded sequences and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    breaking
    0.46
     breaking
    0.46
     uden
    0.45
    Breaking
    0.43
     merk
    0.43
    lvm
    0.41
     testicule
    0.41
    壃
    0.41
    break
    0.41
    bund
    0.41
    POSITIVE LOGITS
     Express
    0.41
     всего
    0.40
     "./
    0.37
     образования
    0.37
     TAP
    0.35
    个
    0.35
     अभि
    0.35
    PixelRatio
    0.35
     испан
    0.35
     gelatin
    0.34
    Act Density 0.002%

    No Known Activations