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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.92
    UserScript
    -0.72
    IVEREF
    -0.71
    RenderAtEndOf
    -0.69
    WriteTagHelper
    -0.69
     otomatig
    -0.68
    ImageContext
    -0.67
     hjälp
    -0.66
    دانشنامهٔ
    -0.66
    jsonwebtoken
    -0.65
    POSITIVE LOGITS
     that
    1.08
     of
    0.81
     the
    0.74
     how
    0.66
    that
    0.62
     from
    0.57
     well
    0.56
     enough
    0.55
     also
    0.53
    <bos>
    0.52
    Act Density 0.008%

    No Known Activations