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

    Neuronpedia

    INDEX
    Explanations

    code and configuration file snippets with keywords like "define," "path," and "license."

    oai_token-act-pair · gemini-2.0-flash

    underscore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -0.75
    d
    -0.70
    t
    -0.69
    r
    -0.67
    de
    -0.67
    m
    -0.65
    st
    -0.65
    le
    -0.64
    n
    -0.64
    ll
    -0.61
    POSITIVE LOGITS
    EndInit
    0.65
    setVerticalGroup
    0.56
     eigenvectors
    0.54
    EnableWeb
    0.54
    minecraftforge
    0.53
    Vidite
    0.52
    SurfaceView
    0.50
    Geplaatst
    0.49
    sidemargin
    0.48
     perfons
    0.47
    Act Density 10.758%

    No Known Activations