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

    Neuronpedia

    INDEX
    Explanations

    DVD

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脚下
    -0.07
     grass
    -0.07
     Counsel
    -0.07
    uras
    -0.07
    兄
    -0.07
    illery
    -0.07
    胸
    -0.06
    INESS
    -0.06
    沿
    -0.06
    NDAR
    -0.06
    POSITIVE LOGITS
     bảng
    0.07
     exclude
    0.07
    ünü
    0.07
     rooted
    0.07
     HDD
    0.07
     testData
    0.07
    תשוב
    0.07
     piè
    0.06
    %'
    0.06
    Compar
    0.06
    Act Density 0.002%

    No Known Activations