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

    Neuronpedia

    INDEX
    Explanations

    tags and their purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    1.21
    ের
    0.95
    ς
    0.93
     سازی
    0.91
    UL
    0.91
    이라면
    0.89
     jika
    0.88
    ی
    0.88
    .=
    0.87
     magnification
    0.86
    POSITIVE LOGITS
    在
    1.33
    م
    1.28
     tags
    1.27
     Tag
    1.19
    问题
    1.18
     Tags
    1.14
    n
    1.14
    re
    1.13
    Tag
    1.11
    m
    1.09
    Act Density 0.014%

    No Known Activations