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

    Neuronpedia

    INDEX
    Explanations

    translations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    完整
    -0.07
    )}"↵
    -0.07
     gel
    -0.07
    肥
    -0.06
    ์และ
    -0.06
    ruk
    -0.06
    (lr
    -0.06
    摘要
    -0.06
     erw
    -0.06
    /fw
    -0.06
    POSITIVE LOGITS
    licher
    0.07
    iselect
    0.07
     QB
    0.07
    erton
    0.06
    ivities
    0.06
     연
    0.06
    日に
    0.06
    alarından
    0.06
     UNITY
    0.06
     ج
    0.06
    Act Density 0.062%

    No Known Activations