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

    Neuronpedia

    INDEX
    Explanations

    prohibiting, allow, hide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    भीर
    0.47
     disqual
    0.47
     তাহাদিগের
    0.46
     stumpage
    0.46
     vaginale
    0.45
     sacking
    0.45
     carbides
    0.45
     sitten
    0.44
    については
    0.44
    磴
    0.43
    POSITIVE LOGITS
     #
    0.52
    #
    0.50
    ws
    0.42
    cul
    0.40
    iron
    0.39
    out
    0.38
    grpc
    0.38
    eg
    0.38
    arm
    0.38
    ji
    0.38
    Act Density 0.000%

    No Known Activations