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

    Neuronpedia

    INDEX
    Explanations

    code coverage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ul
    0.62
     outlay
    0.59
     ставак
    0.58
     umfass
    0.57
    )،
    0.57
     scintillation
    0.54
    ָ
    0.54
    "،
    0.54
    あった
    0.53
     excelled
    0.53
    POSITIVE LOGITS
    ሳሪያ
    0.74
    piej
    0.66
    ために
    0.65
    iary
    0.65
    报告
    0.64
     różne
    0.64
    ての
    0.64
    สำหรับ
    0.63
    त्रे
    0.63
    定价
    0.61
    Act Density 0.001%

    No Known Activations