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

    Neuronpedia

    INDEX
    Explanations

    code structure following HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cómo
    0.41
     त्रासदी
    0.40
    穩
    0.38
     scalp
    0.38
    彧
    0.38
    數據
    0.37
    皚
    0.37
    traumatic
    0.36
    ardan
    0.36
     vody
    0.36
    POSITIVE LOGITS
    <
    0.49
     another
    0.40
    下面的
    0.39
    然后在
    0.38
     <
    0.37
     next
    0.36
    another
    0.36
    之后的
    0.36
     [
    0.35
    /*
    0.34
    Act Density 0.019%

    No Known Activations