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

    Neuronpedia

    INDEX
    Explanations

    classification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gördüğü
    -0.08
    очный
    -0.07
     antibiotics
    -0.07
     photon
    -0.07
     environmentally
    -0.07
     اذا
    -0.07
    oples
    -0.06
     persons
    -0.06
     OK
    -0.06
     George
    -0.06
    POSITIVE LOGITS
    remark
    0.07
    .im
    0.07
    要想
    0.07
     Flo
    0.07
    (li
    0.07
    mouseleave
    0.07
    lah
    0.07
     MSC
    0.07
    leetcode
    0.07
     conflic
    0.06
    Act Density 0.021%

    No Known Activations