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

    Neuronpedia

    INDEX
    Explanations

    gentle petting and reassurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لاث
    0.47
    로서
    0.42
     lesion
    0.41
     failings
    0.41
     треть
    0.40
     üçüncü
    0.40
     rotund
    0.40
    ونک
    0.40
     griev
    0.39
     misuse
    0.39
    POSITIVE LOGITS
     বিবেচনা
    0.46
     kvar
    0.43
    に
    0.42
     اعداد
    0.41
    プレ
    0.41
    एक्स
    0.41
     Pics
    0.41
     DVD
    0.40
    avno
    0.40
     appealing
    0.39
    Act Density 0.008%

    No Known Activations