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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Payroll
    -0.09
     otvor
    -0.08
    лыг
    -0.08
     motherhood
    -0.07
    筆
    -0.07
     Chol
    -0.07
    yev
    -0.07
    开放
    -0.07
     raster
    -0.07
     aankoop
    -0.07
    POSITIVE LOGITS
     반환
    0.08
     pess
    0.07
     retorna
    0.07
     contund
    0.07
     solicit
    0.07
     distancia
    0.07
    }
↵
↵
↵
    0.07
    )↵↵↵
    0.07
     darn
    0.07
    ↵
↵
↵
    0.07
    Act Density 0.025%

    No Known Activations