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

    Neuronpedia

    INDEX
    Explanations

    pack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diffé
    -0.08
    delta
    -0.08
     břez
    -0.07
     Remed
    -0.07
    óż
    -0.07
     Rud
    -0.07
    263
    -0.07
    ísto
    -0.07
     NSInteger
    -0.07
     Hoy
    -0.07
    POSITIVE LOGITS
     Pack
    0.15
     pack
    0.14
    pack
    0.12
    Pack
    0.12
     packs
    0.11
     packed
    0.10
    PACK
    0.10
     PACK
    0.10
    -pack
    0.09
     packing
    0.09
    Act Density 0.018%

    No Known Activations