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

    Neuronpedia

    INDEX
    Explanations

    distributed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Elapsed
    -0.07
    .Ad
    -0.06
     lum
    -0.06
    _sprites
    -0.06
     welt
    -0.06
     betting
    -0.06
     Fired
    -0.06
     showError
    -0.06
    Animation
    -0.06
    Embed
    -0.06
    POSITIVE LOGITS
     Throne
    0.07
    actly
    0.06
    (Configuration
    0.06
    ORG
    0.06
    े।↵
    0.06
    _SYSTEM
    0.06
     JButton
    0.06
     Peoples
    0.06
     vlády
    0.06
    dıkları
    0.06
    Act Density 0.002%

    No Known Activations