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

    Neuronpedia

    INDEX
    Explanations

    Question and answer context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أم
    -0.08
     adorn
    -0.07
     وإذا
    -0.07
    负责同志
    -0.06
     الديمقراطية
    -0.06
     เมษายน
    -0.06
    不存在
    -0.06
    اعة
    -0.06
     minors
    -0.06
    𝓯
    -0.06
    POSITIVE LOGITS
     Character
    0.07
     Want
    0.07
     Vancouver
    0.07
    ℣
    0.07
     Risk
    0.06
    WS
    0.06
     presentation
    0.06
    security
    0.06
     clr
    0.06
    ']),
    0.06
    Act Density 0.015%

    No Known Activations