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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    系列活动
    -0.07
    alloween
    -0.07
    烟花
    -0.07
     adolescente
    -0.06
     svg
    -0.06
    اسب
    -0.06
     pearls
    -0.06
    \Api
    -0.06
    �
    -0.06
    풉
    -0.06
    POSITIVE LOGITS
    𫵷
    0.08
    .optim
    0.07
    -bel
    0.07
    ṗ
    0.07
    iers
    0.07
    厂商
    0.07
     turns
    0.07
    ‑
    0.07
    慷
    0.07
    .ToArray
    0.06
    Act Density 0.018%

    No Known Activations