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

    Neuronpedia

    INDEX
    Explanations

    adverbs and intensifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.84
     Exactos
    -0.77
    PYX
    -0.76
     '{@
    -0.70
    Hentet
    -0.70
    oa̍t
    -0.69
    EndProject
    -0.69
    ImageContext
    -0.69
    WriteTagHelper
    -0.69
    ⓧ
    -0.67
    POSITIVE LOGITS
     the
    0.77
     a
    0.64
     this
    0.57
     shorter
    0.49
     its
    0.48
    $
    0.47
     differing
    0.47
     an
    0.47
     varying
    0.46
     greater
    0.45
    Act Density 0.002%

    No Known Activations