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

    Neuronpedia

    INDEX
    Explanations

    costume clothing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Creator
    -0.08
    排序
    -0.07
     theater
    -0.07
    iffe
    -0.07
    _hat
    -0.06
    .Name
    -0.06
     Opinion
    -0.06
     screening
    -0.06
    _("
    -0.06
     caches
    -0.06
    POSITIVE LOGITS
    比较
    0.07
    enor
    0.07
    �
    0.06
    ‏
    0.06
    双
    0.06
     Lawson
    0.06
    pped
    0.06
    邪
    0.06
    :^
    0.06
    طلق
    0.06
    Act Density 0.030%

    No Known Activations