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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thermostat
    -0.06
    28
    -0.06
     prem
    -0.06
     Prem
    -0.06
     dance
    -0.06
     transporte
    -0.06
     guardar
    -0.06
    rias
    -0.06
     الجز
    -0.06
     ロ
    -0.06
    POSITIVE LOGITS
    却
    0.07
    :]:↵
    0.06
    .Offset
    0.06
     confronted
    0.06
    sss
    0.06
    тив
    0.06
     estud
    0.06
    -loader
    0.06
    />
↵
    0.06
    就会
    0.06
    Act Density 0.037%

    No Known Activations