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

    Neuronpedia

    INDEX
    Explanations

    research databases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reserves
    -0.07
     conducts
    -0.07
     UIL
    -0.07
    Provides
    -0.07
    .Tab
    -0.07
    (Border
    -0.07
    .pr
    -0.06
     Sit
    -0.06
    前线
    -0.06
     exquisite
    -0.06
    POSITIVE LOGITS
     теп
    0.08
    ennai
    0.07
    endale
    0.07
    十年前
    0.07
    朋
    0.06
     grateful
    0.06
    רפואה
    0.06
    离开
    0.06
     سابق
    0.06
    电视剧
    0.06
    Act Density 0.018%

    No Known Activations