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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     their
    -0.66
     things
    -0.62
    GORITH
    -0.61
     something
    -0.59
     a
    -0.57
     his
    -0.55
     its
    -0.54
     civil
    -0.53
     national
    -0.52
    ÉR
    -0.52
    POSITIVE LOGITS
    DockStyle
    1.07
    PerformLayout
    0.91
    ConstraintMaker
    0.81
    GEBURTSDATUM
    0.81
    WithIOException
    0.76
    TagMode
    0.75
     consultato
    0.71
    verwijspagina
    0.70
    setVerticalGroup
    0.69
    ArrowToggle
    0.68
    Act Density 0.068%

    No Known Activations