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

    Neuronpedia

    INDEX
    Explanations

    Updates and configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ani
    0.48
    zan
    0.46
     w
    0.44
    vil
    0.44
    an
    0.44
     뛰어
    0.43
     wal
    0.43
     CO
    0.42
    kova
    0.42
    viel
    0.42
    POSITIVE LOGITS
    ７
    0.52
    Buscar
    0.51
    Migrations
    0.50
    Unexpected
    0.50
    WhiteBalance
    0.49
    Variables
    0.48
    Hasta
    0.48
    RowFilter
    0.47
     élytres
    0.47
    Brewer
    0.47
    Act Density 0.001%

    No Known Activations