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

    Neuronpedia

    INDEX
    Explanations

    Locale/date formatting code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bitcoin
    -0.07
    PATCH
    -0.07
    갤
    -0.07
     عبدال
    -0.07
    indices
    -0.07
    𝐢
    -0.07
    Democratic
    -0.07
    ideos
    -0.07
    fore
    -0.06
    𝄱
    -0.06
    POSITIVE LOGITS
     tung
    0.08
     dct
    0.07
    רות
    0.07
    职能部门
    0.07
    ลอง
    0.07
    _ln
    0.07
     exists
    0.06
    辩证
    0.06
    网店
    0.06
     لهم
    0.06
    Act Density 0.010%

    No Known Activations