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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     five
    -0.77
     Six
    -0.77
     six
    -0.76
     eight
    -0.72
     Five
    -0.69
     Eight
    -0.69
     CreateTagHelper
    -0.69
     pinulongan
    -0.63
    Six
    -0.62
    webElement
    -0.62
    POSITIVE LOGITS
    хьтан
    0.52
     EconPapers
    0.52
    lessly
    0.50
     attes
    0.50
     judiciales
    0.49
    unref
    0.49
    ⓘ
    0.48
    ={`/
    0.47
    andte
    0.47
     anhydride
    0.47
    Act Density 0.001%

    No Known Activations