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

    Neuronpedia

    INDEX
    Explanations

    wear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wear
    -1.28
    Wear
    -0.99
     Wear
    -0.97
     WEAR
    -0.82
    wear
    -0.82
    Diweddarwch
    -0.74
     wears
    -0.73
     faſt
    -0.71
     beſt
    -0.69
    nasel
    -0.68
    POSITIVE LOGITS
     those
    0.58
    ظر
    0.51
     my
    0.50
    ToBounds
    0.45
    <bos>
    0.44
     THOSE
    0.43
    ↵
    0.42
    зм
    0.42
     Resort
    0.40
     Cool
    0.40
    Act Density 0.160%

    No Known Activations