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

    Neuronpedia

    INDEX
    Explanations

    programming keywords, code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    უქ
    0.45
     כת
    0.42
    弧
    0.42
    rible
    0.40
    有点
    0.40
    驱动
    0.39
    መም
    0.39
    MOUNTAINS
    0.39
    enthalt
    0.38
    Dequeue
    0.38
    POSITIVE LOGITS
     refrigerated
    0.44
     Refriger
    0.41
     Diaries
    0.41
     Economics
    0.40
     Indian
    0.40
     Achievement
    0.39
     monuments
    0.39
     favorites
    0.39
     employees
    0.39
     Enc
    0.38
    Act Density 0.000%

    No Known Activations