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

    Neuronpedia

    INDEX
    Explanations

    surrogate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不懂
    -0.07
    ubishi
    -0.07
    洗脸
    -0.07
     adidas
    -0.07
     empez
    -0.07
    ë
    -0.07
    иш
    -0.07
    ości
    -0.06
    ינ
    -0.06
     brit
    -0.06
    POSITIVE LOGITS
    !")
↵
    0.08
     LOCATION
    0.07
    Show
    0.07
    Sort
    0.07
     PROM
    0.07
    row
    0.07
    推�
    0.07
     remaining
    0.06
    詳細
    0.06
    Short
    0.06
    Act Density 0.001%

    No Known Activations