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

    Neuronpedia

    INDEX
    Explanations

    interviews, kings, establish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blob
    0.50
     scolded
    0.50
     diox
    0.48
     Halloween
    0.48
     bureaucratic
    0.48
     Blum
    0.48
     Galvan
    0.48
     Availability
    0.47
     millimeters
    0.47
    testimonials
    0.47
    POSITIVE LOGITS
    ]->
    0.45
    字
    0.41
    MaxValue
    0.40
    Compass
    0.40
     szko
    0.40
    差
    0.40
    样本
    0.40
    માં
    0.39
    maktadır
    0.39
    Logs
    0.39
    Act Density 0.002%

    No Known Activations