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

    Neuronpedia

    INDEX
    Explanations

    represented

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skull
    -0.07
    -dollar
    -0.07
     sweeping
    -0.07
     Cross
    -0.06
    placing
    -0.06
     banned
    -0.06
    老师
    -0.06
     voiced
    -0.06
    stop
    -0.06
    ClientId
    -0.06
    POSITIVE LOGITS
    DataContext
    0.07
     uyar
    0.06
     multi
    0.06
    }%
    0.06
    .LabelControl
    0.06
     ----------------------------------------------------------------------↵
    0.06
    -field
    0.06
    Detect
    0.06
     ArgumentNullException
    0.06
    -length
    0.06
    Act Density 0.000%

    No Known Activations