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

    Neuronpedia

    INDEX
    Explanations

    a) without re-authorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fell
    0.45
    iteits
    0.45
    idelijk
    0.42
    <0x80>
    0.42
    ib
    0.41
    經驗
    0.41
    uzione
    0.41
    ın
    0.40
    ilig
    0.39
    经验
    0.39
    POSITIVE LOGITS
    桦
    0.45
     useParams
    0.45
     지
    0.44
    の色
    0.44
    Thro
    0.42
     알
    0.41
    Recipe
    0.40
     resolv
    0.40
    ยะ
    0.40
     Ảnh
    0.40
    Act Density 0.002%

    No Known Activations