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

    Neuronpedia

    INDEX
    Explanations

    driving words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的热
    0.47
     Verpack
    0.46
    ميل
    0.44
    电信
    0.43
    Koch
    0.41
     Wissenschaften
    0.41
    بو
    0.41
    TARGETTING
    0.40
    غير
    0.40
    trail
    0.39
    POSITIVE LOGITS
     drove
    0.64
     drives
    0.63
     wedges
    0.57
     Drive
    0.55
     drive
    0.54
     driv
    0.52
    MyDrive
    0.51
     driving
    0.49
     Drives
    0.49
     впер
    0.49
    Act Density 0.010%

    No Known Activations