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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.91
    ArrowToggle
    -0.76
    Datuak
    -0.75
     חיצוניים
    -0.72
    ConstraintMaker
    -0.69
    ValueStyle
    -0.69
    TagMode
    -0.67
     Exacts
    -0.66
    WriteTagHelper
    -0.65
    forChild
    -0.65
    POSITIVE LOGITS
     his
    0.54
     supplementary
    0.43
    Say
    0.43
     the
    0.42
     faid
    0.42
    bahnhof
    0.41
     suffic
    0.41
     said
    0.41
     yet
    0.41
    say
    0.41
    Act Density 0.001%

    No Known Activations