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

    Neuronpedia

    INDEX
    Explanations

    specific place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    인
    0.66
    פ
    0.59
    드
    0.59
    čak
    0.57
    ید
    0.56
    어
    0.56
    오
    0.56
    임
    0.56
     Diarsipkan
    0.55
    Д
    0.55
    POSITIVE LOGITS
    2
    0.59
    ana
    0.58
    there
    0.57
    adu
    0.56
    ken
    0.55
    eln
    0.54
    pek
    0.53
    ara
    0.52
    \
    0.52
    kanen
    0.52
    Act Density 0.000%

    No Known Activations