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

    Neuronpedia

    INDEX
    Explanations

    df

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     squeeze
    -0.07
    .tc
    -0.06
     seasoned
    -0.06
     ft
    -0.06
     بعض
    -0.06
    另一半
    -0.06
     mir
    -0.06
    .operation
    -0.06
     Eggs
    -0.06
     Fortress
    -0.06
    POSITIVE LOGITS
    吸取
    0.07
    Ꮠ
    0.07
    Specification
    0.06
    iline
    0.06
    RESP
    0.06
     erv
    0.06
    报警
    0.06
    {-#
    0.06
    روس
    0.06
    照亮
    0.06
    Act Density 0.001%

    No Known Activations