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

    Neuronpedia

    INDEX
    Explanations

    studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.74
    ConstraintMaker
    -0.59
    исленность
    -0.58
    bootstrapcdn
    -0.52
    -0.51
    AddTagHelper
    -0.49
    뀔
    -0.49
    DockStyle
    -0.48
    EndProject
    -0.48
    Autoritní
    -0.47
    POSITIVE LOGITS
     tracks
    0.85
     charts
    0.79
     follows
    0.66
     considers
    0.63
    tracks
    0.62
     studies
    0.62
     judges
    0.61
     ranges
    0.60
     addresses
    0.60
     peers
    0.60
    Act Density 0.001%

    No Known Activations