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

    Neuronpedia

    INDEX
    Explanations

    vehicle identification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freshness
    -0.08
     shelf
    -0.08
     confinement
    -0.08
    ivate
    -0.07
     cue
    -0.07
    ivation
    -0.07
     demand
    -0.07
     Playlist
    -0.07
    esson
    -0.07
     creators
    -0.07
    POSITIVE LOGITS
     автомобиля
    0.10
     goggles
    0.08
     rocker
    0.08
    完整版
    0.08
    Decoded
    0.08
    'om
    0.08
     exceeding
    0.08
     hierzu
    0.08
    _encoded
    0.08
     древес
    0.08
    Act Density 0.003%

    No Known Activations