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

    Neuronpedia

    INDEX
    Explanations

    views

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )item
    -0.07
     ジャ
    -0.06
    mbH
    -0.06
    _CREAT
    -0.06
     رفته
    -0.06
    .PLAIN
    -0.06
     lstm
    -0.06
    longitude
    -0.06
     swollen
    -0.06
     Trust
    -0.06
    POSITIVE LOGITS
     view
    0.07
    sol
    0.07
     views
    0.07
     integrate
    0.07
    公式
    0.07
     nonetheless
    0.06
     Views
    0.06
    ale
    0.06
    eling
    0.06
     Guinness
    0.06
    Act Density 0.017%

    No Known Activations