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

    Neuronpedia

    INDEX
    Explanations

    structural document markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    grilled
    0.58
    roasted
    0.54
    Roasted
    0.54
     ໜອງ
    0.50
     grilled
    0.49
    स्पिटल
    0.48
    Grilled
    0.48
     copyspace
    0.47
     মুক্তিফৌজ
    0.47
     Roasted
    0.47
    POSITIVE LOGITS
    Example
    0.70
     Definition
    0.70
     Example
    0.69
     {\
    0.62
    Definition
    0.61
     Definitions
    0.60
     definition
    0.60
     Assumptions
    0.60
     Remark
    0.59
    }[
    0.57
    Act Density 0.000%

    No Known Activations