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

    Neuronpedia

    INDEX
    Explanations

    8k resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ratulations
    0.49
    urcharge
    0.48
    uo
    0.47
    na
    0.46
    izzeria
    0.45
    ai
    0.45
    icleta
    0.43
     لاع
    0.43
    uen
    0.42
    </strong>
    0.41
    POSITIVE LOGITS
     (
    0.44
    ிறேன்
    0.43
     그런데
    0.43
    ాడు
    0.43
     하지만
    0.43
     But
    0.40
     liegen
    0.39
     Architektur
    0.39
    சிவ
    0.39
    见到
    0.38
    Act Density 0.041%

    No Known Activations