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

    Neuronpedia

    INDEX
    Explanations

    rigid adherence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    舴
    0.48
    舧
    0.45
     подобные
    0.41
     подобных
    0.40
     হর
    0.40
     আকারের
    0.40
     Spots
    0.39
    脷
    0.39
     পাপ
    0.38
     embarrassment
    0.38
    POSITIVE LOGITS
     Strath
    0.41
    Boston
    0.40
    Practical
    0.39
    practical
    0.39
    ubel
    0.39
    heide
    0.38
    썰
    0.38
    boor
    0.38
     Boston
    0.38
    boston
    0.38
    Act Density 0.000%

    No Known Activations