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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stations
    -0.09
    avlj
    -0.08
    stations
    -0.08
    arbeit
    -0.08
    adalafil
    -0.08
     Stations
    -0.07
     shootings
    -0.07
    IMER
    -0.07
     berth
    -0.07
    Raw
    -0.07
    POSITIVE LOGITS
     rim
    0.08
     bordering
    0.08
     tracing
    0.08
     tack
    0.08
     silhou
    0.07
     coastline
    0.07
     mistaken
    0.07
     approaching
    0.07
     illumination
    0.07
     পো
    0.07
    Act Density 0.002%

    No Known Activations