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

    Neuronpedia

    INDEX
    Explanations

    labels followed by values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clam
    0.38
    YEAR
    0.35
    Compared
    0.33
     numbered
    0.33
    numbered
    0.32
    …</
    0.32
    वर्ष
    0.32
    RELATES
    0.32
    Unlike
    0.31
    ceme
    0.31
    POSITIVE LOGITS
     Name
    0.61
     ::
    0.54
    ::
    0.48
    Name
    0.48
    是什么
    0.48
    名称
    0.47
    name
    0.46
    名稱
    0.46
     name
    0.46
    ：
    0.45
    Act Density 0.020%

    No Known Activations