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

    Neuronpedia

    INDEX
    Explanations

    mathematics and learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    you
    0.49
     bijna
    0.49
    (
    0.48
     Alemania
    0.47
     you
    0.47
    ("
    0.47
     zucchero
    0.47
     natuurlijk
    0.46
    你
    0.46
     natürlich
    0.46
    POSITIVE LOGITS
    पणा
    0.47
    䛊
    0.47
     desenvolv
    0.46
    黜
    0.44
     Flutter
    0.42
    Stranger
    0.42
    𒇉
    0.42
    тится
    0.41
    䛺
    0.41
    sstream
    0.41
    Act Density 0.005%

    No Known Activations