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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confrontation
    -0.07
     trạng
    -0.07
     dlouhodob
    -0.06
     arşiv
    -0.06
    customize
    -0.06
    Pagination
    -0.06
    риг
    -0.06
     yola
    -0.06
     lắp
    -0.06
     اصل
    -0.06
    POSITIVE LOGITS
     carbon
    0.07
    UNC
    0.07
     Marketable
    0.07
     volt
    0.06
     Holds
    0.06
    glomer
    0.06
     Toe
    0.06
     slag
    0.06
    _lift
    0.06
     speaks
    0.06
    Act Density 0.089%

    No Known Activations