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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Este
    -0.07
    izzie
    -0.07
    _SO
    -0.07
     dólares
    -0.07
     Kinder
    -0.07
     Hearts
    -0.07
    ocker
    -0.07
     awe
    -0.06
    )object
    -0.06
    ayo
    -0.06
    POSITIVE LOGITS
    ฑ
    0.07
    ция
    0.07
    ением
    0.07
    模式
    0.07
     文件
    0.07
    TestData
    0.07
    (Line
    0.06
    rient
    0.06
     сервис
    0.06
    From
    0.06
    Act Density 0.003%

    No Known Activations