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

    Neuronpedia

    INDEX
    Explanations

    listing pros and advantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sustainability
    0.86
     flexibility
    0.85
     preferring
    0.82
     coatings
    0.82
     Sustainability
    0.80
     downsides
    0.79
     vibrancy
    0.79
     sophistication
    0.78
    诟
    0.77
     weaknesses
    0.77
    POSITIVE LOGITS
     unmistakable
    0.91
     منصوب
    0.91
     unmist
    0.91
     delimited
    0.90
    玧
    0.87
    ۤ
    0.86
    hObject
    0.85
     незакон
    0.85
     autént
    0.84
     unforgettable
    0.84
    Act Density 0.329%

    No Known Activations