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

    Neuronpedia

    INDEX
    Explanations

    not complex or simple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thr
    0.40
     commitments
    0.40
     GW
    0.40
    iec
    0.39
    nahme
    0.38
    wegs
    0.38
    ную
    0.38
    тельным
    0.37
    gw
    0.37
    nek
    0.37
    POSITIVE LOGITS
     ALP
    0.44
    公益
    0.43
     युव
    0.41
     `@
    0.40
    纖
    0.39
     chạm
    0.38
    (@
    0.38
     KENT
    0.38
     calyce
    0.38
     Overview
    0.37
    Act Density 0.000%

    No Known Activations