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

    Neuronpedia

    INDEX
    Explanations

    governmental or official bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ឈ្ម
    0.27
    㑓
    0.27
    眼
    0.27
    িনবার্গ
    0.27
     бясплат
    0.26
    ەیە
    0.26
    ంచరీలు
    0.26
    כן
    0.25
    ທ່ານ
    0.25
    ได้
    0.25
    POSITIVE LOGITS
     of
    0.79
     của
    0.51
     của
    0.48
    of
    0.47
     for
    0.47
     של
    0.46
     ഓഫ്
    0.42
     ऑफ
    0.41
    ของการ
    0.40
     ఆఫ్
    0.40
    Act Density 0.110%

    No Known Activations