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

    Neuronpedia

    INDEX
    Explanations

    fax numbers or radio frequencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ь
    1.41
    Ｄ
    1.37
     elucid
    1.29
     υ
    1.27
     Bail
    1.27
    ﻱ
    1.27
    𝙳
    1.25
    𝘔
    1.23
    ️⃣
    1.23
    Ｂ
    1.22
    POSITIVE LOGITS
    ك
    1.79
    د
    1.76
    ই
    1.75
    ش
    1.67
    특별시
    1.48
    eners
    1.45
    った
    1.44
    č
    1.44
    ことです
    1.41
    britannien
    1.38
    Act Density 0.005%

    No Known Activations