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

    Neuronpedia

    INDEX
    Explanations

    library and book context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ['',
    0.48
    STAT
    0.47
    Butler
    0.44
     ፍ
    0.43
     STAT
    0.41
     Butler
    0.41
     ਸਾ
    0.39
    ทรั
    0.38
    Resource
    0.38
     доступ
    0.38
    POSITIVE LOGITS
    இவ்வாறு
    0.41
    ذی
    0.41
    秒
    0.38
     paj
    0.37
     cycles
    0.37
    cycles
    0.36
    త్త
    0.35
    క్షణ
    0.35
    isone
    0.35
    क्षि
    0.35
    Act Density 0.000%

    No Known Activations