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

    Neuronpedia

    INDEX
    Explanations

    code or data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     план
    -0.06
     relied
    -0.06
    .Base
    -0.06
    กรณ
    -0.06
    zeitig
    -0.06
    ใหญ
    -0.06
     Rotate
    -0.06
     head
    -0.06
    umd
    -0.06
     rotate
    -0.06
    POSITIVE LOGITS
    (prev
    0.07
     isSuccess
    0.07
    -validation
    0.07
    DownList
    0.07
     decreasing
    0.06
     ILogger
    0.06
     �
    0.06
     histograms
    0.06
    isini
    0.06
    /todo
    0.06
    Act Density 0.000%

    No Known Activations