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

    Neuronpedia

    INDEX
    Explanations

    news and weather forecasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encirc
    0.41
     steeper
    0.39
    columns
    0.38
     steepest
    0.38
    solid
    0.37
     tho
    0.37
    chez
    0.37
    name
    0.37
    try
    0.37
    刻
    0.37
    POSITIVE LOGITS
     FOX
    0.64
     NBC
    0.57
     CTV
    0.57
     CBS
    0.57
     ABC
    0.54
    CBS
    0.54
    FOX
    0.54
    CTV
    0.53
    ABC
    0.49
     Ey
    0.45
    Act Density 0.000%

    No Known Activations