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

    Neuronpedia

    INDEX
    Explanations

    specific terms and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ারী
    0.94
    ize
    0.92
    stoffe
    0.90
    عم
    0.89
    告
    0.84
    ul
    0.79
    固
    0.78
    วัสดี
    0.78
    stoffen
    0.77
    ذي
    0.77
    POSITIVE LOGITS
    lighthouse
    0.91
     webhook
    0.87
     ongeveer
    0.87
     nostrils
    0.87
     tweezers
    0.86
     limousine
    0.86
     winkel
    0.85
     entfernt
    0.85
    reflectionCamera
    0.84
     scène
    0.84
    Act Density 0.000%

    No Known Activations