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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :✨
    -0.71
    +#+#
    -0.62
     doInBackground
    -0.61
    AccessorTable
    -0.59
    WriteTagHelper
    -0.58
    glBegin
    -0.56
     betweenstory
    -0.56
    SourceChecksum
    -0.56
    WebVitals
    -0.53
    OGND
    -0.52
    POSITIVE LOGITS
     over
    0.77
     many
    0.74
     around
    0.67
     most
    0.66
    ']>
    0.65
     much
    0.63
     approximately
    0.61
     virtually
    0.60
    ',)
    0.58
     nearly
    0.58
    Act Density 0.001%

    No Known Activations