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

    Neuronpedia

    INDEX
    Explanations

    washing/wash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wash
    -1.81
     Wash
    -1.57
    Wash
    -1.41
    wash
    -1.26
     washed
    -1.21
     washes
    -1.21
     WASH
    -1.13
     washing
    -0.93
    WASH
    -0.87
    washed
    -0.83
    POSITIVE LOGITS
    pence
    0.73
    LookAnd
    0.72
    RegressionTest
    0.72
    sticks
    0.72
     Италијани
    0.69
    іга
    0.67
    ArgsConstructor
    0.67
    tiness
    0.67
     HasFactory
    0.66
    NOPQRST
    0.66
    Act Density 0.175%

    No Known Activations