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

    Neuronpedia

    INDEX
    Explanations

    irreversible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sf
    -0.07
    EMPTY
    -0.07
    .nil
    -0.07
    BF
    -0.06
     ""
    -0.06
     courteous
    -0.06
     acompañ
    -0.06
     Divider
    -0.06
     wanted
    -0.06
     MF
    -0.06
    POSITIVE LOGITS
     irreversible
    0.07
    .Fetch
    0.07
    enerate
    0.07
     nghiên
    0.06
     Manufacturer
    0.06
     Imper
    0.06
     imperial
    0.06
     knitting
    0.06
     يو
    0.06
    Impro
    0.06
    Act Density 0.004%

    No Known Activations