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

    Neuronpedia

    INDEX
    Explanations

    studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᚾ
    -0.08
               
↵
    -0.07
    ﲒ
    -0.07
     diplom
    -0.07
    ואי
    -0.07
    -tech
    -0.06
     부
    -0.06
    �
    -0.06
     ;-)
    -0.06
    ࡐ
    -0.06
    POSITIVE LOGITS
    (fs
    0.08
     erad
    0.08
    (price
    0.08
     مباشرة
    0.07
    📅
    0.07
    ἅ
    0.07
     Geographic
    0.07
    (direction
    0.07
     mktime
    0.07
     الجسم
    0.07
    Act Density 0.044%

    No Known Activations