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

    Neuronpedia

    INDEX
    Explanations

    threats, calories, okay google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    THING
    0.39
     list
    0.39
    '
    0.37
    Jill
    0.36
    בה
    0.35
    託
    0.35
    ilden
    0.35
    里的
    0.34
    주
    0.34
    נת
    0.34
    POSITIVE LOGITS
     หย
    0.43
     transforme
    0.41
     Crown
    0.40
    isht
    0.40
     প্রতিবেদন
    0.40
     tweede
    0.40
    vdots
    0.40
     исче
    0.40
     preparación
    0.39
     desapare
    0.39
    Act Density 0.000%

    No Known Activations