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

    Neuronpedia

    INDEX
    Explanations

    trailing stop / step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सुन
    0.42
    кнове
    0.41
     Assad
    0.40
    ப்பதி
    0.40
    ミ
    0.40
    트
    0.40
    ियों
    0.39
    Thinking
    0.39
    кого
    0.39
    footed
    0.38
    POSITIVE LOGITS
    s
    0.58
     terasa
    0.54
     Guidelines
    0.48
     analiza
    0.48
     المكتب
    0.46
    }{\
    0.45
     fortement
    0.45
     drivetrain
    0.45
     interesa
    0.45
    ().
    0.44
    Act Density 0.003%

    No Known Activations