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

    Neuronpedia

    INDEX
    Explanations

    context window token limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ৫১
    0.42
     fifty
    0.42
     Fifty
    0.41
    fifty
    0.40
     Münster
    0.39
     Sixty
    0.39
    ಎಸ್
    0.39
     fift
    0.39
    ゆ
    0.38
     sixty
    0.38
    POSITIVE LOGITS
    <0xBB>
    0.48
     Thirteen
    0.47
    3
    0.45
     thirteen
    0.45
     ٣
    0.43
    ٣
    0.41
    ૩
    0.38
     Fourteen
    0.38
    十三
    0.37
     Editorial
    0.35
    Act Density 0.006%

    No Known Activations